Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/eef1cde6081ecab1fe84.json +59 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/granite/ibm-granite/granite-3.1-2b-instruct/c0ec6017150d374284d8.json +59 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/01fde036f298da576bb5.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/557109576f3f8cbb33ff.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/71332c436959c6f2b2df.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/d6f52cf989836d27b4a7.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/d70d537ae88aaeeb0e4a.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/3b00e0f0bacc848e2940.json +64 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/55c426279b3ea27aa80c.json +64 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/f5762f0df58a70947038.json +64 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama4_text/tiny-random/llama-4/e7acb642341522b87231.json +82 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/mixtral/dacorvo/Mixtral-tiny/6b5316af77d112e25d37.json +59 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/phi3/microsoft/Phi-3-mini-4k-instruct/cf7a57eb411c245d0587.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/phi3/yujiepan/phi-4-tiny-random/9eeddc59a59f99b6c3e0.json +60 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/310cb4f0cd3300451fd2.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/6755c94eb3261b02a145.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/a4731d4fb6d2288dbc78.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/bd43b5032044547f61a8.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/0814e1811a82e83c84c6.json +65 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen3/Qwen/Qwen3-0.6B/f0f402c449a4aad60bf5.json +88 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/5fd285c0eadaa03f2963.json +66 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/smollm3/HuggingFaceTB/SmolLM3-3B/b0160303296159aa9f20.json +135 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/granite/ibm-granite/granite-3.1-2b-instruct/7c651dfe3d920a47296f.json +59 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/llama/unsloth/Llama-3.2-1B-Instruct/3118cc5f291fc1fc170f.json +64 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/phi3/microsoft/Phi-3-mini-4k-instruct/b91a46877a37ae96bb55.json +63 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen2/Qwen/Qwen2.5-0.5B/c3acbe2da0ec11f56dc9.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen2/Qwen/Qwen2.5-0.5B/f57651a64584dfc4c6c7.json +83 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen3/Qwen/Qwen3-0.6B/af4e0a89cc1f8aa57377.json +88 -0
- neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/smollm3/HuggingFaceTB/SmolLM3-3B/45a9b00b565e1305c4da.json +135 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/compile_flags.json +1 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.done +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.hlo_module.pb +3 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/compile_flags.json +1 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.done +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.hlo_module.pb +3 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/compile_flags.json +1 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.done +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.hlo_module.pb +3 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/compile_flags.json +1 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.done +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.hlo_module.pb +3 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/compile_flags.json +1 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.done +0 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.hlo_module.pb +3 -0
- neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.neff +0 -0
.gitattributes
CHANGED
|
@@ -11126,3 +11126,86 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_4660567457028419303+5860ac52/model.neff fi
|
|
| 11126 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4698872004097027487+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11127 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8325022953710875611+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11128 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8723315026979039343+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11126 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4698872004097027487+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11127 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8325022953710875611+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11128 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8723315026979039343+5860ac52/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11129 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1bcd8486a5476c06ef6c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11130 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1de2e21ffe7389e8ad1d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11131 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f955163eec0c0a80988+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11132 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f955163eec0c0a80988+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11133 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2a1b0305ef3fbebc14b8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11134 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2c56cd496311b411d739+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11135 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2c56cd496311b411d739+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11136 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2d4d844e755ea85a58f8+1408aa15/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11137 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2d4d844e755ea85a58f8+1408aa15/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11138 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2d55f694b62e8f854eb9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11139 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2e7323d127244060130b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11140 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2e7323d127244060130b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11141 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2e8a7fa1e77c0d74a109+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11142 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_2e8a7fa1e77c0d74a109+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11143 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_32db0b2bdbf17f82684a+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11144 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_33dac4fac7b911a97b62+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11145 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3977195999febfa9884a+4e85d101/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11146 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_3977195999febfa9884a+4e85d101/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11147 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_4910ad1451750f3331b2+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11148 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_517620d83434e31618d7+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11149 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_517620d83434e31618d7+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11150 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_573529673e588860faa7+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11151 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_573529673e588860faa7+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11152 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5927db22f81fdb595f6b+e5475efe/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11153 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5927db22f81fdb595f6b+e5475efe/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11154 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5a06a2699238b840e153+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11155 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5d8e8cfd2821a72f68e2+9405b09b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11156 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5d8e8cfd2821a72f68e2+9405b09b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11157 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5ea3e1d7b6cf5f9431b6+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11158 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_5ea3e1d7b6cf5f9431b6+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11159 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_61dbdf738ca076ef369a+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11160 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_61dbdf738ca076ef369a+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11161 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b4f6603f5b4d3a7bdf3+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11162 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_6b4f6603f5b4d3a7bdf3+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11163 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70994cdd91dcdd578ba2+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11164 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_70994cdd91dcdd578ba2+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11165 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_76e4434341e561172edf+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11166 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_76e4434341e561172edf+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11167 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_7cfe5170a9dd6136b7ce+0111e7b7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11168 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_7cfe5170a9dd6136b7ce+0111e7b7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11169 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8093756b582e019dce23+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11170 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_83cf5c47093549d97b56+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11171 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_83f323ead694ba0d7805+74193e2a/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11172 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_83f323ead694ba0d7805+74193e2a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11173 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8c885fa7f628cf2adacd+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11174 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8f87e4680261d822e2a6+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11175 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11176 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9413970e765acfb7b93b+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11177 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_94bb1db91a1d0f3e25dd+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11178 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9739f6cb6ad655504afd+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11179 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9e9600563811116185b7+d378418c/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11180 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9e9600563811116185b7+d378418c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11181 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a09163e5ab9614aecf2d+677eeb9d/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11182 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a1c9a14d12d639c18f60+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11183 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2ecbfaef5906dad2124+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11184 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_a2ecbfaef5906dad2124+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11185 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_ae17583ade4e9b69e281+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11186 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_ae17583ade4e9b69e281+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11187 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b37fdf56be00130a14e9+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11188 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b4e7d72544a2a3a336f5+43d247eb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11189 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b4e7d72544a2a3a336f5+43d247eb/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11190 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b769f1c4c2ced84b948f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11191 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b769f1c4c2ced84b948f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11192 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_bd494b3349fccb264f56+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11193 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_bd494b3349fccb264f56+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11194 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_c3d8546bfef5dce4f40d+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11195 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_cc93bedf1ffea21b58ba+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11196 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_cc93bedf1ffea21b58ba+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11197 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d0dd97edadedf7c69272+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11198 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d0dd97edadedf7c69272+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11199 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d55f7459a88a4b840dd4+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11200 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6a139ec8c530de289c0+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11201 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d6a139ec8c530de289c0+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11202 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d9bfb8a9c556b013ab59+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11203 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_d9bfb8a9c556b013ab59+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11204 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_da2f9ef9477a4d66d1a7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11205 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_e70394de1d791e12c520+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11206 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb91d9a0090e7031df61+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11207 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_eb91d9a0090e7031df61+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11208 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee5a280bc35ab3275432+1fca3866/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11209 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_ee5a280bc35ab3275432+1fca3866/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 11210 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f189f67fe2f9674d0690+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 11211 |
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_f359722ac2fcd615a216+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/eef1cde6081ecab1fe84.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"attention_multiplier": 1.0,
|
| 11 |
+
"embedding_multiplier": 1.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 32,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 64,
|
| 16 |
+
"logits_scaling": 1.0,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 1,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
|
| 25 |
+
"checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
|
| 26 |
+
"continuous_batching": false,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"logical_nc_config": 1,
|
| 33 |
+
"max_batch_size": 1,
|
| 34 |
+
"max_context_length": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"sequence_length": 1024,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": null,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 4,
|
| 50 |
+
"num_hidden_layers": 2,
|
| 51 |
+
"num_key_value_heads": 4,
|
| 52 |
+
"residual_multiplier": 1.0,
|
| 53 |
+
"rms_norm_eps": 1e-06,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 10000.0,
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49152
|
| 59 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/granite/ibm-granite/granite-3.1-2b-instruct/c0ec6017150d374284d8.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_multiplier": 0.015625,
|
| 11 |
+
"embedding_multiplier": 12.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"logits_scaling": 8.0,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 4,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 25 |
+
"checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d",
|
| 26 |
+
"continuous_batching": true,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"logical_nc_config": 1,
|
| 33 |
+
"max_batch_size": 4,
|
| 34 |
+
"max_context_length": 4096,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 4096,
|
| 37 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"sequence_length": 4096,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": null,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 32,
|
| 50 |
+
"num_hidden_layers": 40,
|
| 51 |
+
"num_key_value_heads": 8,
|
| 52 |
+
"residual_multiplier": 0.22,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 5000000.0,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49155
|
| 59 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/01fde036f298da576bb5.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 1,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 512,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 512,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 512,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"tp_degree": 1
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 4,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 4,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 8.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/557109576f3f8cbb33ff.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 2,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": true,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 2,
|
| 32 |
+
"max_context_length": 128,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 128,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 128,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 4,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 4,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 8.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/71332c436959c6f2b2df.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 512,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 512,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 512,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 4,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 4,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 8.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/d6f52cf989836d27b4a7.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 2,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": true,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 1,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 2,
|
| 32 |
+
"max_context_length": 128,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 128,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 128,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 1
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 4,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 4,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 8.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/d70d537ae88aaeeb0e4a.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 4,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 16,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 64,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
| 23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 1024,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 1024,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 1024,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 4,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 4,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 8.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 128256
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/3b00e0f0bacc848e2940.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 23 |
+
"checkpoint_revision": null,
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": false,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 4096,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 4096,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": false,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 4096,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 32.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"unsloth_fixed": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 128256
|
| 64 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/55c426279b3ea27aa80c.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 4,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 23 |
+
"checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
|
| 24 |
+
"continuous_batching": true,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 4,
|
| 32 |
+
"max_context_length": 4096,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 4096,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 4096,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 32.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"unsloth_fixed": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 128256
|
| 64 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama/unsloth/Llama-3.2-1B-Instruct/f5762f0df58a70947038.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 23 |
+
"checkpoint_revision": null,
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": false,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 4096,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 4096,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": false,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 4096,
|
| 41 |
+
"speculation_length": 5,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 32.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"unsloth_fixed": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 128256
|
| 64 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/llama4_text/tiny-random/llama-4/e7acb642341522b87231.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "tiny-random/llama-4",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_chunk_size": 128,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_scale": 0.1,
|
| 9 |
+
"attn_temperature_tuning": 4,
|
| 10 |
+
"cache_implementation": "hybrid",
|
| 11 |
+
"floor_scale": 8192,
|
| 12 |
+
"for_llm_compressor": false,
|
| 13 |
+
"head_dim": 32,
|
| 14 |
+
"hidden_act": "silu",
|
| 15 |
+
"hidden_size": 32,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"interleave_moe_layer_step": 2,
|
| 18 |
+
"intermediate_size": 64,
|
| 19 |
+
"intermediate_size_mlp": 128,
|
| 20 |
+
"layer_types": [
|
| 21 |
+
"chunked_attention",
|
| 22 |
+
"chunked_attention",
|
| 23 |
+
"chunked_attention",
|
| 24 |
+
"full_attention"
|
| 25 |
+
],
|
| 26 |
+
"max_position_embeddings": 1048576,
|
| 27 |
+
"model_type": "llama4_text",
|
| 28 |
+
"moe_layers": [
|
| 29 |
+
1,
|
| 30 |
+
3
|
| 31 |
+
],
|
| 32 |
+
"neuron": {
|
| 33 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 34 |
+
"batch_size": 1,
|
| 35 |
+
"capacity_factor": null,
|
| 36 |
+
"checkpoint_id": "tiny-random/llama-4",
|
| 37 |
+
"checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4",
|
| 38 |
+
"continuous_batching": false,
|
| 39 |
+
"enable_bucketing": false,
|
| 40 |
+
"ep_degree": 1,
|
| 41 |
+
"fused_qkv": false,
|
| 42 |
+
"glu_mlp": true,
|
| 43 |
+
"local_ranks_size": 2,
|
| 44 |
+
"logical_nc_config": 1,
|
| 45 |
+
"max_batch_size": 1,
|
| 46 |
+
"max_context_length": 1024,
|
| 47 |
+
"max_topk": 256,
|
| 48 |
+
"n_active_tokens": 1024,
|
| 49 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 50 |
+
"on_device_sampling": true,
|
| 51 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 52 |
+
"output_logits": false,
|
| 53 |
+
"pp_degree": 1,
|
| 54 |
+
"sequence_length": 1024,
|
| 55 |
+
"speculation_length": 0,
|
| 56 |
+
"start_rank_id": 0,
|
| 57 |
+
"target": null,
|
| 58 |
+
"torch_dtype": "bfloat16",
|
| 59 |
+
"tp_degree": 2
|
| 60 |
+
},
|
| 61 |
+
"no_rope_layers": [
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
1,
|
| 65 |
+
0
|
| 66 |
+
],
|
| 67 |
+
"num_attention_heads": 1,
|
| 68 |
+
"num_experts_per_tok": 1,
|
| 69 |
+
"num_hidden_layers": 4,
|
| 70 |
+
"num_key_value_heads": 1,
|
| 71 |
+
"num_local_experts": 8,
|
| 72 |
+
"output_router_logits": false,
|
| 73 |
+
"rms_norm_eps": 1e-05,
|
| 74 |
+
"rope_scaling": null,
|
| 75 |
+
"rope_theta": 500000.0,
|
| 76 |
+
"router_aux_loss_coef": 0.001,
|
| 77 |
+
"router_jitter_noise": 0.0,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_qk_norm": true,
|
| 81 |
+
"vocab_size": 202048
|
| 82 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/mixtral/dacorvo/Mixtral-tiny/6b5316af77d112e25d37.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "dacorvo/Mixtral-tiny",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MixtralForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"head_dim": 32,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3584,
|
| 14 |
+
"max_position_embeddings": 1024,
|
| 15 |
+
"model_type": "mixtral",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 18 |
+
"batch_size": 1,
|
| 19 |
+
"capacity_factor": null,
|
| 20 |
+
"checkpoint_id": "dacorvo/Mixtral-tiny",
|
| 21 |
+
"checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
|
| 22 |
+
"continuous_batching": false,
|
| 23 |
+
"enable_bucketing": false,
|
| 24 |
+
"ep_degree": 1,
|
| 25 |
+
"fused_qkv": false,
|
| 26 |
+
"glu_mlp": true,
|
| 27 |
+
"local_ranks_size": 2,
|
| 28 |
+
"logical_nc_config": 1,
|
| 29 |
+
"max_batch_size": 1,
|
| 30 |
+
"max_context_length": 1024,
|
| 31 |
+
"max_topk": 256,
|
| 32 |
+
"n_active_tokens": 1024,
|
| 33 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 34 |
+
"on_device_sampling": false,
|
| 35 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 36 |
+
"output_logits": false,
|
| 37 |
+
"pp_degree": 1,
|
| 38 |
+
"sequence_length": 1024,
|
| 39 |
+
"speculation_length": 0,
|
| 40 |
+
"start_rank_id": 0,
|
| 41 |
+
"target": null,
|
| 42 |
+
"torch_dtype": "bfloat16",
|
| 43 |
+
"tp_degree": 2
|
| 44 |
+
},
|
| 45 |
+
"num_attention_heads": 32,
|
| 46 |
+
"num_experts_per_tok": 2,
|
| 47 |
+
"num_hidden_layers": 2,
|
| 48 |
+
"num_key_value_heads": 8,
|
| 49 |
+
"num_local_experts": 8,
|
| 50 |
+
"output_router_logits": false,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_theta": 10000.0,
|
| 53 |
+
"router_aux_loss_coef": 0.001,
|
| 54 |
+
"router_jitter_noise": 0.0,
|
| 55 |
+
"sliding_window": 4096,
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 32000
|
| 59 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/phi3/microsoft/Phi-3-mini-4k-instruct/cf7a57eb411c245d0587.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/Phi-3-mini-4k-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {
|
| 11 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 12 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 13 |
+
},
|
| 14 |
+
"embd_pdrop": 0.0,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 3072,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"max_position_embeddings": 4096,
|
| 20 |
+
"model_type": "phi3",
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 4,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "microsoft/Phi-3-mini-4k-instruct",
|
| 26 |
+
"checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85",
|
| 27 |
+
"continuous_batching": true,
|
| 28 |
+
"enable_bucketing": false,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": true,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"logical_nc_config": 1,
|
| 34 |
+
"max_batch_size": 4,
|
| 35 |
+
"max_context_length": 4096,
|
| 36 |
+
"max_topk": 256,
|
| 37 |
+
"n_active_tokens": 4096,
|
| 38 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 39 |
+
"on_device_sampling": true,
|
| 40 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 41 |
+
"output_logits": false,
|
| 42 |
+
"pp_degree": 1,
|
| 43 |
+
"sequence_length": 4096,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": null,
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 10000.0,
|
| 59 |
+
"sliding_window": 2047,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 32064
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/phi3/yujiepan/phi-4-tiny-random/9eeddc59a59f99b6c3e0.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "yujiepan/phi-4-tiny-random",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {},
|
| 11 |
+
"embd_pdrop": 0.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 16,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 32,
|
| 16 |
+
"max_position_embeddings": 16384,
|
| 17 |
+
"model_type": "phi3",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 1,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "yujiepan/phi-4-tiny-random",
|
| 23 |
+
"checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
|
| 24 |
+
"continuous_batching": false,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 1,
|
| 32 |
+
"max_context_length": 1024,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 1024,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 1024,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 2,
|
| 48 |
+
"num_hidden_layers": 2,
|
| 49 |
+
"num_key_value_heads": 1,
|
| 50 |
+
"original_max_position_embeddings": 16384,
|
| 51 |
+
"partial_rotary_factor": 1.0,
|
| 52 |
+
"resid_pdrop": 0.0,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 250000,
|
| 56 |
+
"sliding_window": null,
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 100352
|
| 60 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/310cb4f0cd3300451fd2.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 1,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": false,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 1,
|
| 56 |
+
"max_context_length": 4096,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 4096,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": true,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 4096,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "float32",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/6755c94eb3261b02a145.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 4,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": true,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 4,
|
| 56 |
+
"max_context_length": 4096,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 4096,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": false,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 4096,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "float16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/a4731d4fb6d2288dbc78.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 2,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": true,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 2,
|
| 56 |
+
"max_context_length": 1024,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 1024,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": false,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 1024,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "float16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/Qwen/Qwen2.5-0.5B/bd43b5032044547f61a8.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 1,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": false,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 1,
|
| 56 |
+
"max_context_length": 4096,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 4096,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": true,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 4096,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen2/yujiepan/qwen2.5-128k-tiny-random/0814e1811a82e83c84c6.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "yujiepan/qwen2.5-128k-tiny-random",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 8,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 16,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention"
|
| 16 |
+
],
|
| 17 |
+
"max_position_embeddings": 32768,
|
| 18 |
+
"max_window_layers": 1,
|
| 19 |
+
"model_type": "qwen2",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 1,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
|
| 25 |
+
"checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
|
| 26 |
+
"continuous_batching": false,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": false,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"logical_nc_config": 1,
|
| 33 |
+
"max_batch_size": 1,
|
| 34 |
+
"max_context_length": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"sequence_length": 1024,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": null,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 4,
|
| 50 |
+
"num_hidden_layers": 2,
|
| 51 |
+
"num_key_value_heads": 2,
|
| 52 |
+
"rms_norm_eps": 1e-06,
|
| 53 |
+
"rope_scaling": {
|
| 54 |
+
"factor": 4.0,
|
| 55 |
+
"original_max_position_embeddings": 32768,
|
| 56 |
+
"rope_type": "yarn",
|
| 57 |
+
"type": "yarn"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"sliding_window": null,
|
| 61 |
+
"tie_word_embeddings": false,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"use_sliding_window": false,
|
| 64 |
+
"vocab_size": 152064
|
| 65 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen3/Qwen/Qwen3-0.6B/f0f402c449a4aad60bf5.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-0.6B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention"
|
| 44 |
+
],
|
| 45 |
+
"max_position_embeddings": 40960,
|
| 46 |
+
"max_window_layers": 28,
|
| 47 |
+
"model_type": "qwen3",
|
| 48 |
+
"neuron": {
|
| 49 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 50 |
+
"batch_size": 4,
|
| 51 |
+
"capacity_factor": null,
|
| 52 |
+
"checkpoint_id": "Qwen/Qwen3-0.6B",
|
| 53 |
+
"checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
|
| 54 |
+
"continuous_batching": true,
|
| 55 |
+
"enable_bucketing": false,
|
| 56 |
+
"ep_degree": 1,
|
| 57 |
+
"fused_qkv": true,
|
| 58 |
+
"glu_mlp": true,
|
| 59 |
+
"local_ranks_size": 2,
|
| 60 |
+
"logical_nc_config": 1,
|
| 61 |
+
"max_batch_size": 4,
|
| 62 |
+
"max_context_length": 4096,
|
| 63 |
+
"max_topk": 256,
|
| 64 |
+
"n_active_tokens": 4096,
|
| 65 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 66 |
+
"on_device_sampling": false,
|
| 67 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 68 |
+
"output_logits": false,
|
| 69 |
+
"pp_degree": 1,
|
| 70 |
+
"sequence_length": 4096,
|
| 71 |
+
"speculation_length": 0,
|
| 72 |
+
"start_rank_id": 0,
|
| 73 |
+
"target": null,
|
| 74 |
+
"torch_dtype": "bfloat16",
|
| 75 |
+
"tp_degree": 2
|
| 76 |
+
},
|
| 77 |
+
"num_attention_heads": 16,
|
| 78 |
+
"num_hidden_layers": 28,
|
| 79 |
+
"num_key_value_heads": 8,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_scaling": null,
|
| 82 |
+
"rope_theta": 1000000,
|
| 83 |
+
"sliding_window": null,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vocab_size": 151936
|
| 88 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/5fd285c0eadaa03f2963.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "optimum-internal-testing/tiny-random-qwen3_moe",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3MoeForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"decoder_sparse_step": 2,
|
| 11 |
+
"head_dim": 32,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 64,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 128,
|
| 16 |
+
"max_position_embeddings": 40960,
|
| 17 |
+
"max_window_layers": 1,
|
| 18 |
+
"mlp_only_layers": [],
|
| 19 |
+
"model_type": "qwen3_moe",
|
| 20 |
+
"moe_intermediate_size": 128,
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 1,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe",
|
| 26 |
+
"checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af",
|
| 27 |
+
"continuous_batching": false,
|
| 28 |
+
"enable_bucketing": false,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": false,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"logical_nc_config": 1,
|
| 34 |
+
"max_batch_size": 1,
|
| 35 |
+
"max_context_length": 1024,
|
| 36 |
+
"max_topk": 256,
|
| 37 |
+
"n_active_tokens": 1024,
|
| 38 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 39 |
+
"on_device_sampling": true,
|
| 40 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 41 |
+
"output_logits": false,
|
| 42 |
+
"pp_degree": 1,
|
| 43 |
+
"sequence_length": 1024,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": null,
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"norm_topk_prob": true,
|
| 51 |
+
"num_attention_heads": 2,
|
| 52 |
+
"num_experts": 8,
|
| 53 |
+
"num_experts_per_tok": 2,
|
| 54 |
+
"num_hidden_layers": 2,
|
| 55 |
+
"num_key_value_heads": 1,
|
| 56 |
+
"output_router_logits": false,
|
| 57 |
+
"rms_norm_eps": 1e-06,
|
| 58 |
+
"rope_scaling": null,
|
| 59 |
+
"rope_theta": 1000000.0,
|
| 60 |
+
"router_aux_loss_coef": 0.001,
|
| 61 |
+
"sliding_window": null,
|
| 62 |
+
"tie_word_embeddings": true,
|
| 63 |
+
"use_cache": true,
|
| 64 |
+
"use_sliding_window": false,
|
| 65 |
+
"vocab_size": 151936
|
| 66 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev6/smollm3/HuggingFaceTB/SmolLM3-3B/b0160303296159aa9f20.json
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "HuggingFaceTB/SmolLM3-3B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"SmolLM3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 65536,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mlp_bias": false,
|
| 55 |
+
"model_type": "smollm3",
|
| 56 |
+
"neuron": {
|
| 57 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 58 |
+
"batch_size": 4,
|
| 59 |
+
"capacity_factor": null,
|
| 60 |
+
"checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
|
| 61 |
+
"checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
|
| 62 |
+
"continuous_batching": true,
|
| 63 |
+
"enable_bucketing": false,
|
| 64 |
+
"ep_degree": 1,
|
| 65 |
+
"fused_qkv": true,
|
| 66 |
+
"glu_mlp": true,
|
| 67 |
+
"local_ranks_size": 2,
|
| 68 |
+
"logical_nc_config": 1,
|
| 69 |
+
"max_batch_size": 4,
|
| 70 |
+
"max_context_length": 4096,
|
| 71 |
+
"max_topk": 256,
|
| 72 |
+
"n_active_tokens": 4096,
|
| 73 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 74 |
+
"on_device_sampling": true,
|
| 75 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
| 76 |
+
"output_logits": false,
|
| 77 |
+
"pp_degree": 1,
|
| 78 |
+
"sequence_length": 4096,
|
| 79 |
+
"speculation_length": 0,
|
| 80 |
+
"start_rank_id": 0,
|
| 81 |
+
"target": null,
|
| 82 |
+
"torch_dtype": "bfloat16",
|
| 83 |
+
"tp_degree": 2
|
| 84 |
+
},
|
| 85 |
+
"no_rope_layer_interval": 4,
|
| 86 |
+
"no_rope_layers": [
|
| 87 |
+
1,
|
| 88 |
+
1,
|
| 89 |
+
1,
|
| 90 |
+
0,
|
| 91 |
+
1,
|
| 92 |
+
1,
|
| 93 |
+
1,
|
| 94 |
+
0,
|
| 95 |
+
1,
|
| 96 |
+
1,
|
| 97 |
+
1,
|
| 98 |
+
0,
|
| 99 |
+
1,
|
| 100 |
+
1,
|
| 101 |
+
1,
|
| 102 |
+
0,
|
| 103 |
+
1,
|
| 104 |
+
1,
|
| 105 |
+
1,
|
| 106 |
+
0,
|
| 107 |
+
1,
|
| 108 |
+
1,
|
| 109 |
+
1,
|
| 110 |
+
0,
|
| 111 |
+
1,
|
| 112 |
+
1,
|
| 113 |
+
1,
|
| 114 |
+
0,
|
| 115 |
+
1,
|
| 116 |
+
1,
|
| 117 |
+
1,
|
| 118 |
+
0,
|
| 119 |
+
1,
|
| 120 |
+
1,
|
| 121 |
+
1,
|
| 122 |
+
0
|
| 123 |
+
],
|
| 124 |
+
"num_attention_heads": 16,
|
| 125 |
+
"num_hidden_layers": 36,
|
| 126 |
+
"num_key_value_heads": 4,
|
| 127 |
+
"pretraining_tp": 2,
|
| 128 |
+
"rms_norm_eps": 1e-06,
|
| 129 |
+
"rope_scaling": null,
|
| 130 |
+
"rope_theta": 5000000.0,
|
| 131 |
+
"sliding_window": null,
|
| 132 |
+
"use_cache": false,
|
| 133 |
+
"use_sliding_window": false,
|
| 134 |
+
"vocab_size": 128256
|
| 135 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/granite/ibm-granite/granite-3.1-2b-instruct/7c651dfe3d920a47296f.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_multiplier": 0.015625,
|
| 11 |
+
"embedding_multiplier": 12.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"logits_scaling": 8.0,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 22 |
+
"batch_size": 4,
|
| 23 |
+
"capacity_factor": null,
|
| 24 |
+
"checkpoint_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 25 |
+
"checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d",
|
| 26 |
+
"continuous_batching": true,
|
| 27 |
+
"enable_bucketing": false,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"logical_nc_config": 1,
|
| 33 |
+
"max_batch_size": 4,
|
| 34 |
+
"max_context_length": 4096,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 4096,
|
| 37 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"sequence_length": 4096,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": null,
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 32,
|
| 50 |
+
"num_hidden_layers": 40,
|
| 51 |
+
"num_key_value_heads": 8,
|
| 52 |
+
"residual_multiplier": 0.22,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 5000000.0,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49155
|
| 59 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/llama/unsloth/Llama-3.2-1B-Instruct/3118cc5f291fc1fc170f.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 8192,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"neuron": {
|
| 19 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 20 |
+
"batch_size": 4,
|
| 21 |
+
"capacity_factor": null,
|
| 22 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 23 |
+
"checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
|
| 24 |
+
"continuous_batching": true,
|
| 25 |
+
"enable_bucketing": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"logical_nc_config": 1,
|
| 31 |
+
"max_batch_size": 4,
|
| 32 |
+
"max_context_length": 4096,
|
| 33 |
+
"max_topk": 256,
|
| 34 |
+
"n_active_tokens": 4096,
|
| 35 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 36 |
+
"on_device_sampling": true,
|
| 37 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 38 |
+
"output_logits": false,
|
| 39 |
+
"pp_degree": 1,
|
| 40 |
+
"sequence_length": 4096,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": null,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 32.0,
|
| 54 |
+
"high_freq_factor": 4.0,
|
| 55 |
+
"low_freq_factor": 1.0,
|
| 56 |
+
"original_max_position_embeddings": 8192,
|
| 57 |
+
"rope_type": "llama3"
|
| 58 |
+
},
|
| 59 |
+
"rope_theta": 500000.0,
|
| 60 |
+
"tie_word_embeddings": true,
|
| 61 |
+
"unsloth_fixed": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 128256
|
| 64 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/phi3/microsoft/Phi-3-mini-4k-instruct/b91a46877a37ae96bb55.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/Phi-3-mini-4k-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {
|
| 11 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 12 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 13 |
+
},
|
| 14 |
+
"embd_pdrop": 0.0,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 3072,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 8192,
|
| 19 |
+
"max_position_embeddings": 4096,
|
| 20 |
+
"model_type": "phi3",
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 4,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "microsoft/Phi-3-mini-4k-instruct",
|
| 26 |
+
"checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85",
|
| 27 |
+
"continuous_batching": true,
|
| 28 |
+
"enable_bucketing": false,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": true,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"logical_nc_config": 1,
|
| 34 |
+
"max_batch_size": 4,
|
| 35 |
+
"max_context_length": 4096,
|
| 36 |
+
"max_topk": 256,
|
| 37 |
+
"n_active_tokens": 4096,
|
| 38 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 39 |
+
"on_device_sampling": true,
|
| 40 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 41 |
+
"output_logits": false,
|
| 42 |
+
"pp_degree": 1,
|
| 43 |
+
"sequence_length": 4096,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": null,
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": null,
|
| 58 |
+
"rope_theta": 10000.0,
|
| 59 |
+
"sliding_window": 2047,
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 32064
|
| 63 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen2/Qwen/Qwen2.5-0.5B/c3acbe2da0ec11f56dc9.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 4,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": true,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 4,
|
| 56 |
+
"max_context_length": 4096,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 4096,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": false,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 4096,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "float16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen2/Qwen/Qwen2.5-0.5B/f57651a64584dfc4c6c7.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 896,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 4864,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention"
|
| 38 |
+
],
|
| 39 |
+
"max_position_embeddings": 32768,
|
| 40 |
+
"max_window_layers": 24,
|
| 41 |
+
"model_type": "qwen2",
|
| 42 |
+
"neuron": {
|
| 43 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 44 |
+
"batch_size": 1,
|
| 45 |
+
"capacity_factor": null,
|
| 46 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 47 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 48 |
+
"continuous_batching": false,
|
| 49 |
+
"enable_bucketing": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"logical_nc_config": 1,
|
| 55 |
+
"max_batch_size": 1,
|
| 56 |
+
"max_context_length": 4096,
|
| 57 |
+
"max_topk": 256,
|
| 58 |
+
"n_active_tokens": 4096,
|
| 59 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 60 |
+
"on_device_sampling": true,
|
| 61 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 62 |
+
"output_logits": false,
|
| 63 |
+
"pp_degree": 1,
|
| 64 |
+
"sequence_length": 4096,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": null,
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/qwen3/Qwen/Qwen3-0.6B/af4e0a89cc1f8aa57377.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-0.6B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention"
|
| 44 |
+
],
|
| 45 |
+
"max_position_embeddings": 40960,
|
| 46 |
+
"max_window_layers": 28,
|
| 47 |
+
"model_type": "qwen3",
|
| 48 |
+
"neuron": {
|
| 49 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 50 |
+
"batch_size": 4,
|
| 51 |
+
"capacity_factor": null,
|
| 52 |
+
"checkpoint_id": "Qwen/Qwen3-0.6B",
|
| 53 |
+
"checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
|
| 54 |
+
"continuous_batching": true,
|
| 55 |
+
"enable_bucketing": false,
|
| 56 |
+
"ep_degree": 1,
|
| 57 |
+
"fused_qkv": true,
|
| 58 |
+
"glu_mlp": true,
|
| 59 |
+
"local_ranks_size": 2,
|
| 60 |
+
"logical_nc_config": 1,
|
| 61 |
+
"max_batch_size": 4,
|
| 62 |
+
"max_context_length": 4096,
|
| 63 |
+
"max_topk": 256,
|
| 64 |
+
"n_active_tokens": 4096,
|
| 65 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 66 |
+
"on_device_sampling": false,
|
| 67 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 68 |
+
"output_logits": false,
|
| 69 |
+
"pp_degree": 1,
|
| 70 |
+
"sequence_length": 4096,
|
| 71 |
+
"speculation_length": 0,
|
| 72 |
+
"start_rank_id": 0,
|
| 73 |
+
"target": null,
|
| 74 |
+
"torch_dtype": "bfloat16",
|
| 75 |
+
"tp_degree": 2
|
| 76 |
+
},
|
| 77 |
+
"num_attention_heads": 16,
|
| 78 |
+
"num_hidden_layers": 28,
|
| 79 |
+
"num_key_value_heads": 8,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_scaling": null,
|
| 82 |
+
"rope_theta": 1000000,
|
| 83 |
+
"sliding_window": null,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vocab_size": 151936
|
| 88 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.3.1.dev7/smollm3/HuggingFaceTB/SmolLM3-3B/45a9b00b565e1305c4da.json
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "HuggingFaceTB/SmolLM3-3B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"SmolLM3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 65536,
|
| 53 |
+
"max_window_layers": 28,
|
| 54 |
+
"mlp_bias": false,
|
| 55 |
+
"model_type": "smollm3",
|
| 56 |
+
"neuron": {
|
| 57 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 58 |
+
"batch_size": 4,
|
| 59 |
+
"capacity_factor": null,
|
| 60 |
+
"checkpoint_id": "HuggingFaceTB/SmolLM3-3B",
|
| 61 |
+
"checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1",
|
| 62 |
+
"continuous_batching": true,
|
| 63 |
+
"enable_bucketing": false,
|
| 64 |
+
"ep_degree": 1,
|
| 65 |
+
"fused_qkv": true,
|
| 66 |
+
"glu_mlp": true,
|
| 67 |
+
"local_ranks_size": 2,
|
| 68 |
+
"logical_nc_config": 1,
|
| 69 |
+
"max_batch_size": 4,
|
| 70 |
+
"max_context_length": 4096,
|
| 71 |
+
"max_topk": 256,
|
| 72 |
+
"n_active_tokens": 4096,
|
| 73 |
+
"neuronxcc_version": "2.21.18209.0+043b1bf7",
|
| 74 |
+
"on_device_sampling": true,
|
| 75 |
+
"optimum_neuron_version": "0.3.1.dev7",
|
| 76 |
+
"output_logits": false,
|
| 77 |
+
"pp_degree": 1,
|
| 78 |
+
"sequence_length": 4096,
|
| 79 |
+
"speculation_length": 0,
|
| 80 |
+
"start_rank_id": 0,
|
| 81 |
+
"target": null,
|
| 82 |
+
"torch_dtype": "bfloat16",
|
| 83 |
+
"tp_degree": 2
|
| 84 |
+
},
|
| 85 |
+
"no_rope_layer_interval": 4,
|
| 86 |
+
"no_rope_layers": [
|
| 87 |
+
1,
|
| 88 |
+
1,
|
| 89 |
+
1,
|
| 90 |
+
0,
|
| 91 |
+
1,
|
| 92 |
+
1,
|
| 93 |
+
1,
|
| 94 |
+
0,
|
| 95 |
+
1,
|
| 96 |
+
1,
|
| 97 |
+
1,
|
| 98 |
+
0,
|
| 99 |
+
1,
|
| 100 |
+
1,
|
| 101 |
+
1,
|
| 102 |
+
0,
|
| 103 |
+
1,
|
| 104 |
+
1,
|
| 105 |
+
1,
|
| 106 |
+
0,
|
| 107 |
+
1,
|
| 108 |
+
1,
|
| 109 |
+
1,
|
| 110 |
+
0,
|
| 111 |
+
1,
|
| 112 |
+
1,
|
| 113 |
+
1,
|
| 114 |
+
0,
|
| 115 |
+
1,
|
| 116 |
+
1,
|
| 117 |
+
1,
|
| 118 |
+
0,
|
| 119 |
+
1,
|
| 120 |
+
1,
|
| 121 |
+
1,
|
| 122 |
+
0
|
| 123 |
+
],
|
| 124 |
+
"num_attention_heads": 16,
|
| 125 |
+
"num_hidden_layers": 36,
|
| 126 |
+
"num_key_value_heads": 4,
|
| 127 |
+
"pretraining_tp": 2,
|
| 128 |
+
"rms_norm_eps": 1e-06,
|
| 129 |
+
"rope_scaling": null,
|
| 130 |
+
"rope_theta": 5000000.0,
|
| 131 |
+
"sliding_window": null,
|
| 132 |
+
"use_cache": false,
|
| 133 |
+
"use_sliding_window": false,
|
| 134 |
+
"vocab_size": 128256
|
| 135 |
+
}
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1"]
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b453d9412b470017be7adc71575130eacf5a7c8277a6b4424e0751ceecaf33df
|
| 3 |
+
size 1291
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1023294089137432912+e30acd3a/model.neff
ADDED
|
Binary file (31.7 kB). View file
|
|
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1"]
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b36a2c38093715f8f1064e95c504963c4eefb108483ea5177b7a9b67c594c14c
|
| 3 |
+
size 1584
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10907752543637211265+e30acd3a/model.neff
ADDED
|
Binary file (31.7 kB). View file
|
|
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1"]
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4cd8c9bb30b80bbae17c37817e07cd72864c7431ffe820db04cc90175ae6c79
|
| 3 |
+
size 1146
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_10945286243277389437+e30acd3a/model.neff
ADDED
|
Binary file (31.7 kB). View file
|
|
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1"]
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dcdc83733e2a421bdc65e593bd84b693b25114c7d871cc5383cf3ac18dbfdfb
|
| 3 |
+
size 1584
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_11400907432531398953+e30acd3a/model.neff
ADDED
|
Binary file (31.7 kB). View file
|
|
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1"]
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4243920bcc2c2a24a52dfa8987ab9473deb4d78a4670a61445d473982e64db7b
|
| 3 |
+
size 1291
|
neuronxcc-2.21.18209.0+043b1bf7/MODULE_12311847081050718470+e30acd3a/model.neff
ADDED
|
Binary file (31.7 kB). View file
|
|
|