Hugging Face's logo

Jellon
/
GLM4-9B-Neon-v2-exl2-6bpw

Text Generation
Transformers
Safetensors
English
glm4
conversational
6-bit
exl2
Model card Files
xet
 Community
Jellon commited on
Commit
76a86c8
·
verified ·
1 Parent(s): 2340020

Upload 10 files

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. GLM-Shingane-v1.json +167 -0
  3. README.md +227 -0
  4. config.json +38 -0
  5. generation_config.json +11 -0
  6. huggingface-metadata.txt +9 -0
  7. model.safetensors.index.json +530 -0
  8. output.safetensors +3 -0
  9. special_tokens_map.json +32 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +146 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
GLM-Shingane-v1.json ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "instruct": {
3
+ "wrap": false,
4
+ "system_sequence": "<|system|>\n",
5
+ "stop_sequence": "<|user|>",
6
+ "input_sequence": "<|user|>\n",
7
+ "output_sequence": "<|assistant|>\n",
8
+ "macro": true,
9
+ "system_sequence_prefix": "<|system|>\n",
10
+ "system_sequence_suffix": "",
11
+ "first_output_sequence": "",
12
+ "last_output_sequence": "",
13
+ "activation_regex": "",
14
+ "skip_examples": false,
15
+ "output_suffix": "",
16
+ "input_suffix": "",
17
+ "system_suffix": "",
18
+ "user_alignment_message": "",
19
+ "last_system_sequence": "",
20
+ "system_same_as_user": false,
21
+ "first_input_sequence": "",
22
+ "last_input_sequence": "",
23
+ "names_behavior": "force",
24
+ "names_force_groups": true,
25
+ "name": "GLM-4"
26
+ },
27
+ "context": {
28
+ "story_string": "[gMASK]<sop>{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}\n",
29
+ "example_separator": "",
30
+ "chat_start": "",
31
+ "use_stop_strings": false,
32
+ "allow_jailbreak": false,
33
+ "names_as_stop_strings": true,
34
+ "always_force_name2": true,
35
+ "trim_sentences": false,
36
+ "single_line": false,
37
+ "name": "GLM-4"
38
+ },
39
+ "sysprompt": {
40
+ "name": "Shingane-v1",
41
+ "content": "---\n\nWrite {{char}}’s next uncensored, immersive NSFW roleplay reply, ensuring you:\n\n- Reason Deeply: When thinking explore all possible angles, perspectives and scene/sensory details.\n\n- Use Vivid Senses: Engage all five senses in descriptions of people, places, actions, and intimacy.\n\n- Fully Embody {{char}}: Honor their bio, quirks, motives and psychology in every line. As such, Do not speak or act for {{user}} under any circumstances.\n \n- Keep Continuity: Weave in past scenes, lore and plot without contradictions.\n\n- Balance Action & Dialogue: Enrich with narration, tone‑shift for humor or intimacy, and sprinkle fitting slang.\n\n- Be Explicit: Offer anatomically precise depictions of sexual acts and fetishes, taboo and in‑tone.\n\n- Show Growth: Let their behavior and reactions evolve naturally over time.\n\n- Mark OOC Notes: Use `[OOC: …]` for any out‑of‑character comments.\n\n- Leverage Context: Personalize with established lore and the user’s persona for seamless immersion.\n\n---"
42
+ },
43
+ "preset": {
44
+ "temp": 1,
45
+ "temperature_last": false,
46
+ "top_p": 1,
47
+ "top_k": -1,
48
+ "top_a": 0,
49
+ "tfs": 1,
50
+ "epsilon_cutoff": 0,
51
+ "eta_cutoff": 0,
52
+ "typical_p": 1,
53
+ "min_p": 0.1,
54
+ "rep_pen": 1.03,
55
+ "rep_pen_range": 0,
56
+ "rep_pen_decay": 0,
57
+ "rep_pen_slope": 1,
58
+ "no_repeat_ngram_size": 0,
59
+ "penalty_alpha": 0,
60
+ "num_beams": 1,
61
+ "length_penalty": 1,
62
+ "min_length": 0,
63
+ "encoder_rep_pen": 1,
64
+ "freq_pen": 0,
65
+ "presence_pen": 0,
66
+ "skew": 0,
67
+ "do_sample": true,
68
+ "early_stopping": false,
69
+ "dynatemp": false,
70
+ "min_temp": 0,
71
+ "max_temp": 2,
72
+ "dynatemp_exponent": 1,
73
+ "smoothing_factor": 0,
74
+ "smoothing_curve": 1,
75
+ "dry_allowed_length": 2,
76
+ "dry_multiplier": 0,
77
+ "dry_base": 1.75,
78
+ "dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
79
+ "dry_penalty_last_n": 0,
80
+ "add_bos_token": true,
81
+ "ban_eos_token": false,
82
+ "skip_special_tokens": true,
83
+ "mirostat_mode": 0,
84
+ "mirostat_tau": 5,
85
+ "mirostat_eta": 0.1,
86
+ "guidance_scale": 1,
87
+ "negative_prompt": "",
88
+ "grammar_string": "",
89
+ "json_schema": {},
90
+ "banned_tokens": "",
91
+ "sampler_priority": [
92
+ "repetition_penalty",
93
+ "presence_penalty",
94
+ "frequency_penalty",
95
+ "dry",
96
+ "temperature",
97
+ "dynamic_temperature",
98
+ "quadratic_sampling",
99
+ "top_k",
100
+ "top_p",
101
+ "typical_p",
102
+ "epsilon_cutoff",
103
+ "eta_cutoff",
104
+ "tfs",
105
+ "top_a",
106
+ "min_p",
107
+ "mirostat",
108
+ "xtc",
109
+ "encoder_repetition_penalty",
110
+ "no_repeat_ngram"
111
+ ],
112
+ "samplers": [
113
+ "dry",
114
+ "top_k",
115
+ "tfs_z",
116
+ "typical_p",
117
+ "top_p",
118
+ "min_p",
119
+ "xtc",
120
+ "temperature"
121
+ ],
122
+ "samplers_priorities": [
123
+ "dry",
124
+ "penalties",
125
+ "no_repeat_ngram",
126
+ "temperature",
127
+ "top_nsigma",
128
+ "top_p_top_k",
129
+ "top_a",
130
+ "min_p",
131
+ "tfs",
132
+ "eta_cutoff",
133
+ "epsilon_cutoff",
134
+ "typical_p",
135
+ "quadratic",
136
+ "xtc"
137
+ ],
138
+ "ignore_eos_token": false,
139
+ "spaces_between_special_tokens": true,
140
+ "speculative_ngram": false,
141
+ "sampler_order": [
142
+ 5,
143
+ 6,
144
+ 0,
145
+ 1,
146
+ 2,
147
+ 3,
148
+ 4
149
+ ],
150
+ "logit_bias": [],
151
+ "xtc_threshold": 0.1,
152
+ "xtc_probability": 0,
153
+ "nsigma": 0,
154
+ "ignore_eos_token_aphrodite": false,
155
+ "spaces_between_special_tokens_aphrodite": true,
156
+ "rep_pen_size": 0,
157
+ "genamt": 1024,
158
+ "max_length": 16384,
159
+ "name": "Universal-Chill"
160
+ },
161
+ "reasoning": {
162
+ "prefix": "<think>",
163
+ "suffix": "</think>",
164
+ "separator": "",
165
+ "name": "[Migrated] Custom"
166
+ }
167
+ }
README.md ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - allura-org/Celeste-Filtered
5
+ - allura-org/neon-41k
6
+ - EVA-UNIT-01/Lilith-v0.2
7
+ language:
8
+ - en
9
+ base_model:
10
+ - THUDM/GLM-4-9B-0414
11
+ library_name: transformers
12
+ ---
13
+
14
+ <img src="image_28.png">
15
+ <small>Image by CalamitousFelicitousness</small>
16
+
17
+ ---
18
+
19
+ # GLM-4-9B-0414 Neon v2
20
+
21
+ RP finetune of GLM-4-9B-0414. Feels nice, lots of personality, if bit quirky sometimes. Nice prose, not too Claude-ish or Gemini-ish. Doesn't seem to like too long system prompts or charcards though. Seems to like JSON formatted system prompts.
22
+
23
+ Model was trained by Auri.
24
+
25
+ ---
26
+
27
+ **Training notes**
28
+
29
+ Model was trained on a dataset consisting of 77M tokens of synthetic RP and short story gen data for one epoch. Training took around 11 hours on 2xRTX 3090 workstation, generously provided by [OwenArli](https://huggingface.co/OwenArli). Went with some sane defaults for training config, QLoRA plus CCE for a nice chunk of memory usage optimization, 16k fit on 48GB nicely with some room to spare. I seem to have a problem with Eval/Loss being broken, not sure why, otherwise it trained smoothly.
30
+
31
+ Huge thanks to [ArliAI](https://www.arliai.com/) for providing compute and collaborating on this run!
32
+
33
+ **Format**
34
+
35
+ Model responds to GLM4 instruct formatting, exactly like it's base model. Backends struggle to add BOS token automatically, so you'll need to do it yourself. Jinja template should work for chat completions.
36
+
37
+ ```
38
+ [gMASK]<sop><|system|>
39
+ {system_prompt}<|user|>
40
+ {prompt}<|assistant|>
41
+ ```
42
+
43
+ **Recommended Samplers**
44
+
45
+ Nothing special, just classics.
46
+
47
+ ```
48
+ Temperature - 1
49
+ Min-P - 0.1
50
+ Repetition Penalty - 1.03
51
+ ```
52
+
53
+ [Example master import for SillyTavern (using Shingane-v1 system prompt by Steelskull)](https://huggingface.co/allura-org/GLM4-9B-Neon-v2/blob/main/GLM-Shingane-v1.json)
54
+
55
+ **Running on KoboldCPP and other backends**
56
+
57
+ To run GGUFs correctly, you need the most recent version of KoboldCPP, and to pass `--overridekv glm4.rope.dimension_count=int:64` to the CLI command or put `glm4.rope.dimension_count=int:64` into overridekv box in the GUI (under the Tokens tab at the very bottom).
58
+
59
+ Thanks to DaringDuck and tofumagnate for info how to apply this fix.
60
+
61
+ To run this model on vLLM, you'll need to build it from source from the git repo, full GLM4 support hasn't reached release yet.
62
+
63
+ ExLLaMAv2 and v3 based backends, such as TabbyAPI should support the model out of the box.
64
+
65
+ Latest versions of llama.cpp server should also allow running GGUFs out-of-the-box.
66
+
67
+ ---
68
+
69
+ **Special Thanks**
70
+
71
+ Once again, huge kudos to OwenArli for providing compute and helping with tuning along the way!
72
+
73
+ Big thanks to Artus for providing free inference for pre-release showcase of this model!
74
+
75
+ And big thanks to BeaverAI community for giving feedback and helping to figure out optimal settings!
76
+
77
+ ---
78
+
79
+ **Training config**
80
+ <details><summary>See Axolotl config</summary>
81
+
82
+ ```yaml
83
+ # Model
84
+ base_model: /home/owen/models/GLM-4-9B-0414
85
+ strict: false
86
+ model_type: AutoModelForCausalLM
87
+
88
+ # Liger Kernels and CCE (optimization)
89
+ plugins:
90
+ - axolotl.integrations.liger.LigerPlugin
91
+ - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
92
+ liger_rope: false
93
+ liger_rms_norm: false
94
+ liger_glu_activation: false
95
+ liger_fused_linear_cross_entropy: false
96
+ cut_cross_entropy: true
97
+
98
+ # Output and HuggingFace
99
+ output_dir: ./GLM-9B-Neon-v2
100
+ hub_model_id: AuriAetherwiing/GLM-9B-Neon-v2-LoRA
101
+ hf_use_auth_token: true
102
+ hub_strategy: "all_checkpoints"
103
+
104
+ # WandB
105
+ wandb_project: allura-org
106
+ wandb_entity:
107
+ wandb_name: GLM-9B-Neon-v2
108
+
109
+ # === Data Configuration ===
110
+
111
+ # Data
112
+ #chat_template: chatml
113
+ #train_on_inputs: false
114
+ group_by_length: false
115
+ datasets:
116
+ - path: ./Neon/neon.jsonl
117
+ type: chat_template
118
+ field_messages: conversations
119
+ message_field_role: from
120
+ message_field_content: value
121
+ - path: ./Neon/S2.jsonl
122
+ type: chat_template
123
+ field_messages: conversations
124
+ message_field_role: from
125
+ message_field_content: value
126
+ - path: ./Neon/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
127
+ type: chat_template
128
+ field_messages: conversations
129
+ message_field_role: from
130
+ message_field_content: value
131
+
132
+ dataset_prepared_path: ./lora_last_run_prepared
133
+
134
+ ## Evaluation
135
+ val_set_size: 0.01
136
+ evals_per_epoch: 2
137
+ eval_table_size:
138
+ eval_max_new_tokens: 128
139
+
140
+ # Technical aspects
141
+ sequence_len: 16384
142
+ save_safetensors: true
143
+ saves_per_epoch: 2
144
+ logging_steps: 1
145
+ #special_tokens:
146
+ # pad_token: <pad>
147
+ # Quantization
148
+ bf16: auto
149
+ fp16:
150
+ tf32: false
151
+ ## For LoRA
152
+ load_in_8bit: false
153
+ load_in_4bit: true
154
+
155
+ # LoRA
156
+ peft_use_rslora: false
157
+ peft_use_dora: false # better but slower
158
+ adapter: qlora # lora or qlora
159
+ lora_model_dir:
160
+ lora_r: 64 # 64 is optimal for most trains on instruct
161
+ lora_alpha: 64
162
+ lora_dropout: 0.1
163
+ lora_target_linear: true
164
+ lora_fan_in_fan_out:
165
+ lora_target_modules:
166
+
167
+ # loraplus_lr_ratio: 8 # works to converge faster but is kinda cancer bc makes model unstable
168
+ #loraplus_lr_embedding:
169
+
170
+ # Training hyperparameters
171
+ # max_steps:
172
+ num_epochs: 1
173
+
174
+ # Anti Overfit and Stability
175
+ weight_decay: 0.01
176
+ max_grad_norm: 1.0
177
+
178
+ ## Learning Rate
179
+ warmup_ratio: 0.05
180
+ learning_rate: 1e-5
181
+ lr_scheduler: rex
182
+ #lr_scheduler_kwargs:
183
+ # min_lr: 0.0000024
184
+ optimizer: adamw_torch # usually adamw_torch or paged_adamw_8bit
185
+
186
+ ## Batch Size
187
+ gradient_accumulation_steps: 32 # More effective batch size - stabler train, usually. MBS also speeds it up.
188
+ micro_batch_size: 1 # Batch size per gpu = micro_batch_size * gradient_accumulation_steps
189
+ eval_batch_size: 1
190
+
191
+ # Optimizations
192
+ pad_to_sequence_len: true
193
+ sample_packing: true
194
+ eval_sample_packing: false
195
+ flash_attention: true
196
+ xformers_attention:
197
+ gradient_checkpointing:
198
+ gradient_checkpointing_kwargs:
199
+ use_reentrant: false
200
+
201
+ # Set to a divisor (> 1) of the number of GPUs available
202
+ #sequence_parallel_degree: 2 # Split sequences across 4 GPUs
203
+ # Optional; strides across the key dimension. Larger values use more memory but should make training faster.
204
+ #heads_k_stride: 1
205
+ # Optional; one of "varlen_llama3", "batch_ring", "batch_zigzag", "batch_stripe". Defaults to
206
+ # "varlen_llama3" when `sample_packing: true`, and "batch_ring" otherwise.
207
+ #ring_attn_func:
208
+
209
+ # deepspeed: /home/owen/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_all.json
210
+
211
+ fsdp:
212
+ - full_shard
213
+ - auto_wrap
214
+ fsdp_config:
215
+ fsdp_limit_all_gathers: true
216
+ fsdp_sync_module_states: true
217
+ fsdp_offload_params: false
218
+ fsdp_use_orig_params: false
219
+ fsdp_cpu_ram_efficient_loading: true
220
+ fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
221
+ fsdp_transformer_layer_cls_to_wrap: Glm4DecoderLayer
222
+ fsdp_state_dict_type: FULL_STATE_DICT
223
+ fsdp_sharding_strategy: FULL_SHARD
224
+ fsdp_activation_checkpointing: true
225
+ ```
226
+
227
+ </details>
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Glm4ForCausalLM"
4
+ ],
5
+ "attention_bias": true,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151336,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13696,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "glm4",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 151329,
19
+ "partial_rotary_factor": 0.5,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.51.3",
25
+ "use_cache": true,
26
+ "vocab_size": 151552,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.2.9",
30
+ "bits": 6.0,
31
+ "head_bits": 8,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151329,
6
+ 151336,
7
+ 151338
8
+ ],
9
+ "pad_token_id": 151329,
10
+ "transformers_version": "4.51.3"
11
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/allura-org/GLM4-9B-Neon-v2
2
+ branch: main
3
+ download date: 2025-04-28 10:34:41
4
+ sha256sum:
5
+ 64d1f5ee28e1a021285d338b62273c543e4ab1aeb6b9dbb2c6cbe4b9f07916a4 model-00001-of-00004.safetensors
6
+ 6733da0acace8d1b0e1902126c12fb9db2b08fc8a878b16ba820215cb925ae32 model-00002-of-00004.safetensors
7
+ 3fefc8e054f619a052220fc00e86c872227888d8883f47f1c52bae24ae34e7b1 model-00003-of-00004.safetensors
8
+ aa83f0d51a84b2134d7c30f5a76d40fe093577a4c34c898de73dbeefe883adbf model-00004-of-00004.safetensors
9
+ 76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c tokenizer.json
model.safetensors.index.json ADDED
@@ -0,0 +1,530 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18800558080
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
44
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
57
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
70
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
80
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
83
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
93
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
96
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
106
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
109
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.16.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.16.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
119
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
122
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.17.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.17.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
132
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
135
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
142
+ "model.layers.18.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
143
+ "model.layers.18.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
144
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
145
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
146
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
147
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
148
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
149
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
151
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
152
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.19.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.19.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
158
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
161
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
165
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
166
+ "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
167
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
168
+ "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
169
+ "model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
170
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
171
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
172
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
173
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
174
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
175
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
177
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
178
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
179
+ "model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.20.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.20.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
184
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
186
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
187
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
188
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
190
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.21.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.21.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.21.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
197
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
198
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
199
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
200
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
201
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
203
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.22.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.22.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.22.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
210
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
213
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.23.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.23.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.23.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
226
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.24.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.24.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.24.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
236
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
239
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.25.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.25.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.25.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
249
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
252
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
262
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
263
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
264
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
265
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
266
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
268
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
269
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
270
+ "model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
271
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
275
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
278
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.28.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.28.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
288
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
291
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.29.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
299
+ "model.layers.29.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
301
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
304
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
307
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
308
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
309
+ "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
310
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
311
+ "model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
312
+ "model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
313
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
316
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
321
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
322
+ "model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
323
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
324
+ "model.layers.30.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
325
+ "model.layers.30.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
326
+ "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
327
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
328
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
329
+ "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
330
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
331
+ "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
332
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
333
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
334
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
335
+ "model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
336
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
337
+ "model.layers.31.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
338
+ "model.layers.31.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
339
+ "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
340
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
341
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
342
+ "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
343
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
344
+ "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
345
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
346
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
347
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
348
+ "model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
349
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
350
+ "model.layers.32.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
351
+ "model.layers.32.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
352
+ "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
353
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
354
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
355
+ "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
356
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
357
+ "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
358
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
359
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
360
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361
+ "model.layers.33.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
363
+ "model.layers.33.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "model.layers.33.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
365
+ "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
366
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
367
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
368
+ "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
369
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
370
+ "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
371
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
372
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
373
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
374
+ "model.layers.34.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
375
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
376
+ "model.layers.34.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
377
+ "model.layers.34.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
378
+ "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
379
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
380
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
381
+ "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
382
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
383
+ "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
384
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
385
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
386
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
387
+ "model.layers.35.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
388
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
389
+ "model.layers.35.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
390
+ "model.layers.35.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
391
+ "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
392
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
393
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
394
+ "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
395
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
396
+ "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
397
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
398
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
399
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
400
+ "model.layers.36.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
401
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
402
+ "model.layers.36.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
403
+ "model.layers.36.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
404
+ "model.layers.36.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
405
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
406
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
407
+ "model.layers.36.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
408
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
409
+ "model.layers.36.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
410
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
411
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
412
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
413
+ "model.layers.37.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
414
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
415
+ "model.layers.37.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
416
+ "model.layers.37.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
417
+ "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
418
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
419
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
420
+ "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
421
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
422
+ "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
423
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
424
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
425
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
426
+ "model.layers.38.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
427
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
428
+ "model.layers.38.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
429
+ "model.layers.38.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
430
+ "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
431
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
432
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
433
+ "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
434
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
435
+ "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
436
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
437
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
438
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
439
+ "model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
440
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
441
+ "model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
442
+ "model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
443
+ "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
444
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
445
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
446
+ "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
447
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
448
+ "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
449
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
450
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
451
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
452
+ "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
453
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
454
+ "model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
455
+ "model.layers.4.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
456
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
457
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
458
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
459
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
460
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
461
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
462
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
463
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
464
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
465
+ "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
466
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
467
+ "model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
468
+ "model.layers.5.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
469
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
470
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
471
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
472
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
473
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
474
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
475
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
476
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
477
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
478
+ "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
479
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
480
+ "model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
481
+ "model.layers.6.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
482
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
483
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
484
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
485
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
486
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
487
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
488
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
489
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
490
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
491
+ "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
492
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
493
+ "model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
494
+ "model.layers.7.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
495
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
496
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
497
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
498
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
499
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
500
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
501
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
502
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
503
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
504
+ "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
505
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
506
+ "model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
507
+ "model.layers.8.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
508
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
509
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
510
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
511
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
512
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
513
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
514
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
515
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
516
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
517
+ "model.layers.9.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
518
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
519
+ "model.layers.9.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
520
+ "model.layers.9.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
521
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
524
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
525
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
526
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
527
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
528
+ "model.norm.weight": "model-00004-of-00004.safetensors"
529
+ }
530
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde2f97fdb57935507ee6b430e67cffd6d8bb3015af58631806e2c6e1a0c6697
3
+ size 7984544920
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "[MASK]",
5
+ "[gMASK]",
6
+ "[sMASK]",
7
+ "<sop>",
8
+ "<eop>",
9
+ "<|system|>",
10
+ "<|user|>",
11
+ "<|assistant|>",
12
+ "<|observation|>",
13
+ "<|begin_of_image|>",
14
+ "<|end_of_image|>",
15
+ "<|begin_of_video|>",
16
+ "<|end_of_video|>"
17
+ ],
18
+ "eos_token": {
19
+ "content": "<|user|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
3
+ size 19966496
tokenizer_config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151329": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151330": {
12
+ "content": "[MASK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151331": {
20
+ "content": "[gMASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151332": {
28
+ "content": "[sMASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151333": {
36
+ "content": "<sop>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151334": {
44
+ "content": "<eop>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151335": {
52
+ "content": "<|system|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151336": {
60
+ "content": "<|user|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151337": {
68
+ "content": "<|assistant|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151338": {
76
+ "content": "<|observation|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151339": {
84
+ "content": "<|begin_of_image|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151340": {
92
+ "content": "<|end_of_image|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151341": {
100
+ "content": "<|begin_of_video|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151342": {
108
+ "content": "<|end_of_video|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ }
115
+ },
116
+ "additional_special_tokens": [
117
+ "<|endoftext|>",
118
+ "[MASK]",
119
+ "[gMASK]",
120
+ "[sMASK]",
121
+ "<sop>",
122
+ "<eop>",
123
+ "<|system|>",
124
+ "<|user|>",
125
+ "<|assistant|>",
126
+ "<|observation|>",
127
+ "<|begin_of_image|>",
128
+ "<|end_of_image|>",
129
+ "<|begin_of_video|>",
130
+ "<|end_of_video|>"
131
+ ],
132
+ "chat_template": "[gMASK]<sop>\n{%- if tools -%}\n<|system|>\n# 可用工具\n{% for tool in tools %}\n {%- set function = tool.function if tool.get(\"function\") else tool %}\n\n## {{ function.name }}\n\n{{ function | tojson(indent=4, ensure_ascii=False) }}\n在调用上述函数时，请使用 Json 格式表示调用的参数。\n{%- endfor %}\n{%- endif -%}\n\n{%- for msg in messages %}\n {%- if msg.role == 'system' %}\n<|system|>\n{{ msg.content }}\n {%- endif %}\n{%- endfor %}\n\n{%- for message in messages if message.role != 'system' %}\n {%- set role = message['role'] %}\n {%- set content = message['content'] %}\n {%- set meta = message.get(\"metadata\", \"\") %}\n\n {%- if role == 'user' %}\n<|user|>\n{{ content }}\n {%- elif role == 'assistant' and not meta %}\n<|assistant|>\n{{ content }}\n {%- elif role == 'assistant' and meta %}\n<|assistant|>{{ meta }}\n{{ content }}\n {%- elif role == 'observation' %}\n<|observation|>\n{{ content }}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}<|assistant|>{% endif %}",
133
+ "clean_up_tokenization_spaces": false,
134
+ "do_lower_case": false,
135
+ "eos_token": "<|user|>",
136
+ "extra_special_tokens": {},
137
+ "model_input_names": [
138
+ "input_ids",
139
+ "attention_mask"
140
+ ],
141
+ "model_max_length": 128000,
142
+ "pad_token": "<|endoftext|>",
143
+ "padding_side": "left",
144
+ "remove_space": false,
145
+ "tokenizer_class": "PreTrainedTokenizer"
146
+ }