Upload LlamaForCausalLM
Browse files- config.json +74 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"eos_token_id": 128001,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 131072,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pretraining_tp": 1,
|
| 21 |
+
"quantization_config": {
|
| 22 |
+
"backend": null,
|
| 23 |
+
"batch_size": 1,
|
| 24 |
+
"bits": 3,
|
| 25 |
+
"block_name_to_quantize": null,
|
| 26 |
+
"cache_block_outputs": true,
|
| 27 |
+
"checkpoint_format": "gptq",
|
| 28 |
+
"damp_percent": 0.1,
|
| 29 |
+
"dataset": null,
|
| 30 |
+
"desc_act": true,
|
| 31 |
+
"exllama_config": {
|
| 32 |
+
"version": 1
|
| 33 |
+
},
|
| 34 |
+
"group_size": 128,
|
| 35 |
+
"max_input_length": null,
|
| 36 |
+
"meta": {
|
| 37 |
+
"damp_auto_increment": 0.01,
|
| 38 |
+
"damp_percent": 0.05,
|
| 39 |
+
"mse": 0.0,
|
| 40 |
+
"quantizer": [
|
| 41 |
+
"gptqmodel:4.0.0-dev"
|
| 42 |
+
],
|
| 43 |
+
"static_groups": false,
|
| 44 |
+
"true_sequential": true,
|
| 45 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 46 |
+
"v2": false,
|
| 47 |
+
"v2_alpha": 0.25
|
| 48 |
+
},
|
| 49 |
+
"model_seqlen": null,
|
| 50 |
+
"module_name_preceding_first_block": null,
|
| 51 |
+
"modules_in_block_to_quantize": null,
|
| 52 |
+
"pad_token_id": null,
|
| 53 |
+
"quant_method": "gptq",
|
| 54 |
+
"sym": true,
|
| 55 |
+
"tokenizer": null,
|
| 56 |
+
"true_sequential": true,
|
| 57 |
+
"use_cuda_fp16": false,
|
| 58 |
+
"use_exllama": true
|
| 59 |
+
},
|
| 60 |
+
"rms_norm_eps": 1e-05,
|
| 61 |
+
"rope_scaling": {
|
| 62 |
+
"factor": 8.0,
|
| 63 |
+
"high_freq_factor": 4.0,
|
| 64 |
+
"low_freq_factor": 1.0,
|
| 65 |
+
"original_max_position_embeddings": 8192,
|
| 66 |
+
"rope_type": "llama3"
|
| 67 |
+
},
|
| 68 |
+
"rope_theta": 500000.0,
|
| 69 |
+
"tie_word_embeddings": false,
|
| 70 |
+
"torch_dtype": "float16",
|
| 71 |
+
"transformers_version": "4.51.1",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 128256
|
| 74 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": 128001,
|
| 6 |
+
"temperature": 0.6,
|
| 7 |
+
"top_p": 0.95,
|
| 8 |
+
"transformers_version": "4.51.1"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f977a2feb24ff2820a69978704bcc60e706bfb926b2fb526fe7768fb6e302a13
|
| 3 |
+
size 4853712424
|