MikeRoz commited on
Commit
a7e2cc1
1 Parent(s): 5edd02c

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ license_name: qwen
5
+ license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
6
+ base_model: Qwen/Qwen2.5-72B-Instruct
7
+ tags:
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: 72B-Qwen2.5-Kunou-v1
11
+ results: []
12
+ ---
13
+
14
+ ![Kunou](https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1/resolve/main/knn.png)
15
+
16
+ # 72B-Qwen2.5-Kunou-v1
17
+
18
+ I do not really have anything planned for this model other than it being a generalist, and Roleplay Model? It was just something made and planned in minutes.
19
+ <br>Same with the 14 and 32B version.
20
+ <br>Kunou's the name of an OC I worked on for a couple of years, for a... fanfic. mmm...
21
+
22
+ A kind-of successor to L3-70B-Euryale-v2.2 in all but name? I'm keeping Stheno/Euryale lineage to Llama series for now.
23
+ <br>I had a version made on top of Nemotron, a supposed Euryale 2.4 but that flopped hard, it was not my cup of tea.
24
+ <br>This version is basically a better, more cleaned up Dataset used on Euryale and Stheno.
25
+
26
+ Recommended Model Settings | *Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.*
27
+ ```
28
+ Prompt Format: ChatML
29
+ Temperature: 1.1
30
+ min_p: 0.1
31
+ ```
32
+
33
+
34
+ Future-ish plans:
35
+ <br>\- Complete this model series.
36
+ <br>\- Further refine the Datasets used for quality, more secondary chats, more creative-related domains. (Inspired by Drummer)
37
+ <br>\- Work on my other incomplete projects. About half a dozen on the backburner for a while now.
38
+
39
+ Special thanks to my wallet for funding this, my juniors who share a single braincell between them, and my current national service.
40
+ <br>Stay safe. There have been more emergency calls, more incidents this holiday season.
41
+
42
+ Also sorry for the inactivity. Life was in the way. It still is, just less so, for now. Burnout is a thing, huh?
43
+
44
+ https://sao10k.carrd.co/ for contact.
45
+
46
+ ---
47
+
48
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
49
+ <details><summary>See axolotl config</summary>
50
+
51
+ axolotl version: `0.5.2`
52
+ ```yaml
53
+ base_model: Qwen/Qwen2.5-72B-Instruct
54
+ model_type: AutoModelForCausalLM
55
+ tokenizer_type: AutoTokenizer
56
+
57
+ load_in_8bit: false
58
+ load_in_4bit: false
59
+ strict: false
60
+ sequence_len: 16384
61
+ bf16: auto
62
+ fp16:
63
+ tf32: false
64
+ flash_attention: true
65
+
66
+ adapter: lora
67
+ lora_model_dir:
68
+ lora_r: 128
69
+ lora_alpha: 16
70
+ lora_dropout: 0.1
71
+ lora_target_linear: true
72
+ lora_fan_in_fan_out:
73
+ peft_use_rslora: true
74
+
75
+ # Data
76
+ dataset_prepared_path: last_run_prepared
77
+ datasets:
78
+ - path: datasets/amoral-full-sys-prompt.json # Unalignment Data - Cleaned Up from Original, Split to its own file
79
+ type: customchatml
80
+ - path: datasets/mimi-superfix-RP-filtered-fixed.json # RP / Creative-Instruct Data
81
+ type: customchatml
82
+ - path: datasets/hespera-smartshuffle.json # Hesperus-v2-Instruct Data
83
+ type: customchatml
84
+ warmup_steps: 15
85
+
86
+ plugins:
87
+ - axolotl.integrations.liger.LigerPlugin
88
+ liger_rope: true
89
+ liger_rms_norm: true
90
+ liger_layer_norm: true
91
+ liger_glu_activation: true
92
+ liger_fused_linear_cross_entropy: true
93
+
94
+ # Iterations
95
+ num_epochs: 1
96
+
97
+ # Batching
98
+ gradient_accumulation_steps: 4
99
+ micro_batch_size: 1
100
+ gradient_checkpointing: "unsloth"
101
+
102
+ # Optimizer
103
+ optimizer: paged_ademamix_8bit
104
+ lr_scheduler: cosine
105
+ learning_rate: 0.000004
106
+ weight_decay: 0.1
107
+ max_grad_norm: 25.0
108
+
109
+ # Iterations
110
+ num_epochs: 1
111
+
112
+ # Misc
113
+ deepspeed: ./deepspeed_configs/zero3_bf16.json
114
+ ```
115
+
116
+ </details><br>
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Sao10K/72B-Qwen2.5-Kunou-v1",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 29568,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 80,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.47.0",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064,
29
+ "quantization_config": {
30
+ "quant_method": "exl2",
31
+ "version": "0.2.3",
32
+ "bits": 8.0,
33
+ "head_bits": 8,
34
+ "calibration": {
35
+ "rows": 115,
36
+ "length": 2048,
37
+ "dataset": "(default)"
38
+ }
39
+ }
40
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.46.3"
14
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1
2
+ branch: main
3
+ download date: 2024-12-07 15:07:42
4
+ sha256sum:
5
+ 3101104a601abcc05ec7b72d85fa955656f3c1c96b57c0bf92c83c60983e6c15 model-00001-of-00015.safetensors
6
+ 72d6663d6e9434593b71c9aac36abd4d307c2301dd86daac1c5136dbcac5cc75 model-00002-of-00015.safetensors
7
+ 09628f2421f3a25a4b83f63d3b80b251b49299b66a785de84e399384335d3eb5 model-00003-of-00015.safetensors
8
+ 3c8ca75f6eb316b05b498786971765e87373373b249061aa4671ba1e2cd90f50 model-00004-of-00015.safetensors
9
+ 9a634b91dcfbf099cc147cf891ad7b022e14dc367330a90a48979821d1213d78 model-00005-of-00015.safetensors
10
+ 5810783cb4545cbd2212f825760fb45743dc6067ed579fc4e307c8a467e72730 model-00006-of-00015.safetensors
11
+ 6f76f17ce31ea488b4286bae4f2f98b26f05b31a6f028f558ae83afbc6d259a8 model-00007-of-00015.safetensors
12
+ 7aa76a41a730af80411135a547fe02c3fefbe881c54ca3efcaeb66a133df2990 model-00008-of-00015.safetensors
13
+ 959a709817bd1dedf455dfed20e46b9c287084100c18df4d278769cad6cc31ab model-00009-of-00015.safetensors
14
+ 5fcf4073d3c2636e2f26d1180ee50e202f430a669a497276334fed1522a99f26 model-00010-of-00015.safetensors
15
+ 90e09e47af4594658ed8fd758ad2cbe430209aeae6a9c4b20283f5a617017de4 model-00011-of-00015.safetensors
16
+ 9d78c2bc795753944e4255f40943d14e44e4fc834a12335d903135ad2efefe08 model-00012-of-00015.safetensors
17
+ 1e1246d78af2b20ab00ba210d6d9af75bc6e76921dd8fd4a38f8d7760b636c86 model-00013-of-00015.safetensors
18
+ 8b907e4e3a82371ec4fd7a62e045735e31cff2921f56d81e98dc3df8ec018479 model-00014-of-00015.safetensors
19
+ f016cd6314f34469cb1b188f232ae424b1cfa1c9c884fe6dbd068ee1e30242ba model-00015-of-00015.safetensors
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1,970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 145412407296
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00001-of-00015.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00015.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00015.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00015.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00015.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00015.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00003-of-00015.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00015.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00015.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00015.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00015.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00015.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00015.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00015.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00015.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00005-of-00015.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00015.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00015.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00006-of-00015.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00006-of-00015.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00006-of-00015.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00006-of-00015.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00006-of-00015.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00007-of-00015.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00007-of-00015.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00007-of-00015.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00007-of-00015.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00007-of-00015.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00007-of-00015.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00008-of-00015.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00008-of-00015.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00008-of-00015.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00008-of-00015.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00008-of-00015.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00009-of-00015.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00009-of-00015.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00009-of-00015.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00009-of-00015.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00009-of-00015.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00009-of-00015.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00010-of-00015.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00010-of-00015.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00010-of-00015.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00010-of-00015.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00010-of-00015.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00011-of-00015.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00011-of-00015.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00011-of-00015.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00011-of-00015.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00011-of-00015.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00011-of-00015.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00012-of-00015.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00012-of-00015.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
740
+ "model.layers.64.input_layernorm.weight": "model-00012-of-00015.safetensors",
741
+ "model.layers.64.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
742
+ "model.layers.64.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
743
+ "model.layers.64.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
744
+ "model.layers.64.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
745
+ "model.layers.64.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
746
+ "model.layers.64.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
747
+ "model.layers.64.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
748
+ "model.layers.64.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
749
+ "model.layers.64.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
750
+ "model.layers.64.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
751
+ "model.layers.64.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
752
+ "model.layers.65.input_layernorm.weight": "model-00012-of-00015.safetensors",
753
+ "model.layers.65.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
754
+ "model.layers.65.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
755
+ "model.layers.65.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
756
+ "model.layers.65.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
757
+ "model.layers.65.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
758
+ "model.layers.65.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
759
+ "model.layers.65.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
760
+ "model.layers.65.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
761
+ "model.layers.65.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
762
+ "model.layers.65.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
763
+ "model.layers.65.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
764
+ "model.layers.66.input_layernorm.weight": "model-00012-of-00015.safetensors",
765
+ "model.layers.66.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
766
+ "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
767
+ "model.layers.66.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
768
+ "model.layers.66.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
769
+ "model.layers.66.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
770
+ "model.layers.66.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
771
+ "model.layers.66.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
772
+ "model.layers.66.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
773
+ "model.layers.66.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
774
+ "model.layers.66.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
775
+ "model.layers.66.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
776
+ "model.layers.67.input_layernorm.weight": "model-00013-of-00015.safetensors",
777
+ "model.layers.67.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
778
+ "model.layers.67.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
779
+ "model.layers.67.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
780
+ "model.layers.67.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
781
+ "model.layers.67.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
782
+ "model.layers.67.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
783
+ "model.layers.67.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
784
+ "model.layers.67.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
785
+ "model.layers.67.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
786
+ "model.layers.67.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
787
+ "model.layers.67.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
788
+ "model.layers.68.input_layernorm.weight": "model-00013-of-00015.safetensors",
789
+ "model.layers.68.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
790
+ "model.layers.68.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
791
+ "model.layers.68.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
792
+ "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
793
+ "model.layers.68.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
794
+ "model.layers.68.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
795
+ "model.layers.68.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
796
+ "model.layers.68.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
797
+ "model.layers.68.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
798
+ "model.layers.68.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
799
+ "model.layers.68.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
800
+ "model.layers.69.input_layernorm.weight": "model-00013-of-00015.safetensors",
801
+ "model.layers.69.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
802
+ "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
803
+ "model.layers.69.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
804
+ "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
805
+ "model.layers.69.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
806
+ "model.layers.69.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
807
+ "model.layers.69.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
808
+ "model.layers.69.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
809
+ "model.layers.69.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
810
+ "model.layers.69.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
811
+ "model.layers.69.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
812
+ "model.layers.7.input_layernorm.weight": "model-00013-of-00015.safetensors",
813
+ "model.layers.7.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
814
+ "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
815
+ "model.layers.7.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
816
+ "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
817
+ "model.layers.7.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
818
+ "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
819
+ "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
820
+ "model.layers.7.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
821
+ "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
822
+ "model.layers.7.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
823
+ "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
824
+ "model.layers.70.input_layernorm.weight": "model-00013-of-00015.safetensors",
825
+ "model.layers.70.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
826
+ "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
827
+ "model.layers.70.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
828
+ "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
829
+ "model.layers.70.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
830
+ "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
831
+ "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
832
+ "model.layers.70.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
833
+ "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
834
+ "model.layers.70.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
835
+ "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
836
+ "model.layers.71.input_layernorm.weight": "model-00013-of-00015.safetensors",
837
+ "model.layers.71.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
838
+ "model.layers.71.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
839
+ "model.layers.71.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
840
+ "model.layers.71.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
841
+ "model.layers.71.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
842
+ "model.layers.71.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
843
+ "model.layers.71.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
844
+ "model.layers.71.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
845
+ "model.layers.71.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
846
+ "model.layers.71.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
847
+ "model.layers.71.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
848
+ "model.layers.72.input_layernorm.weight": "model-00014-of-00015.safetensors",
849
+ "model.layers.72.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
850
+ "model.layers.72.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
851
+ "model.layers.72.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
852
+ "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
853
+ "model.layers.72.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
854
+ "model.layers.72.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
855
+ "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
856
+ "model.layers.72.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
857
+ "model.layers.72.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
858
+ "model.layers.72.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
859
+ "model.layers.72.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
860
+ "model.layers.73.input_layernorm.weight": "model-00014-of-00015.safetensors",
861
+ "model.layers.73.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
862
+ "model.layers.73.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
863
+ "model.layers.73.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
864
+ "model.layers.73.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
865
+ "model.layers.73.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
866
+ "model.layers.73.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
867
+ "model.layers.73.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
868
+ "model.layers.73.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
869
+ "model.layers.73.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
870
+ "model.layers.73.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
871
+ "model.layers.73.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
872
+ "model.layers.74.input_layernorm.weight": "model-00014-of-00015.safetensors",
873
+ "model.layers.74.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
874
+ "model.layers.74.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
875
+ "model.layers.74.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
876
+ "model.layers.74.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
877
+ "model.layers.74.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
878
+ "model.layers.74.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
879
+ "model.layers.74.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
880
+ "model.layers.74.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
881
+ "model.layers.74.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
882
+ "model.layers.74.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
883
+ "model.layers.74.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
884
+ "model.layers.75.input_layernorm.weight": "model-00014-of-00015.safetensors",
885
+ "model.layers.75.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
886
+ "model.layers.75.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
887
+ "model.layers.75.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
888
+ "model.layers.75.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
889
+ "model.layers.75.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
890
+ "model.layers.75.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
891
+ "model.layers.75.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
892
+ "model.layers.75.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
893
+ "model.layers.75.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
894
+ "model.layers.75.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
895
+ "model.layers.75.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
896
+ "model.layers.76.input_layernorm.weight": "model-00014-of-00015.safetensors",
897
+ "model.layers.76.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
898
+ "model.layers.76.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
899
+ "model.layers.76.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
900
+ "model.layers.76.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
901
+ "model.layers.76.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
902
+ "model.layers.76.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
903
+ "model.layers.76.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
904
+ "model.layers.76.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
905
+ "model.layers.76.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
906
+ "model.layers.76.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
907
+ "model.layers.76.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
908
+ "model.layers.77.input_layernorm.weight": "model-00015-of-00015.safetensors",
909
+ "model.layers.77.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
910
+ "model.layers.77.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
911
+ "model.layers.77.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
912
+ "model.layers.77.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
913
+ "model.layers.77.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
914
+ "model.layers.77.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
915
+ "model.layers.77.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
916
+ "model.layers.77.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
917
+ "model.layers.77.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
918
+ "model.layers.77.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
919
+ "model.layers.77.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
920
+ "model.layers.78.input_layernorm.weight": "model-00015-of-00015.safetensors",
921
+ "model.layers.78.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
922
+ "model.layers.78.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
923
+ "model.layers.78.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
924
+ "model.layers.78.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
925
+ "model.layers.78.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
926
+ "model.layers.78.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
927
+ "model.layers.78.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
928
+ "model.layers.78.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
929
+ "model.layers.78.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
930
+ "model.layers.78.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
931
+ "model.layers.78.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
932
+ "model.layers.79.input_layernorm.weight": "model-00015-of-00015.safetensors",
933
+ "model.layers.79.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
934
+ "model.layers.79.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
935
+ "model.layers.79.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
936
+ "model.layers.79.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
937
+ "model.layers.79.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
938
+ "model.layers.79.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
939
+ "model.layers.79.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
940
+ "model.layers.79.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
941
+ "model.layers.79.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
942
+ "model.layers.79.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
943
+ "model.layers.79.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
944
+ "model.layers.8.input_layernorm.weight": "model-00015-of-00015.safetensors",
945
+ "model.layers.8.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
946
+ "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
947
+ "model.layers.8.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
948
+ "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
949
+ "model.layers.8.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
950
+ "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
951
+ "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
952
+ "model.layers.8.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
953
+ "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
954
+ "model.layers.8.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
955
+ "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
956
+ "model.layers.9.input_layernorm.weight": "model-00015-of-00015.safetensors",
957
+ "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
958
+ "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
959
+ "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
960
+ "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
961
+ "model.layers.9.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
962
+ "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
963
+ "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
964
+ "model.layers.9.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
965
+ "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
966
+ "model.layers.9.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
967
+ "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
968
+ "model.norm.weight": "model-00015-of-00015.safetensors"
969
+ }
970
+ }
output-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3db70661d642a19ea9d0738cd5fb42853ee72f4835d9523a808dd5f3ef57d1cd
3
+ size 8495675848
output-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5da0b3f2b11526895d9b1e62572af305226d7023c9410598e28f5d1f0b6065a
3
+ size 8583583292
output-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d31ca996af12bd725858e9ea0ca59635e5271ee3cbcc233f12ceafa57c3f31
3
+ size 8570884486
output-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5897335fe5a31d0e8a261c52845813a5867954d64316b1b3ed77228b360beeba
3
+ size 8499628076
output-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d702f9cd7baa281a8935acb75453d7ed81897e066589706195b14fd0dd9e2ab
3
+ size 8400672172
output-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02aea99fae35c096bf07606ebc1568cab9251d24f89a23b92198c6a6a7141277
3
+ size 8534980490
output-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58ca0851feacb99ae4d9541cb096f47f553a1bafe89f2af5a319b25ca109e42
3
+ size 8416132924
output-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7c2b9971f0b32202bab50c702624503a6f5ce89508581af22153d9b97ee4278
3
+ size 8472922040
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff