Hugging Face's logo

CodCodingCode
/
qwen-deepseek-conversational-V2.1

TensorBoard
Safetensors
qwen3
Model card Files
xet
Metrics Community
CodCodingCode commited on
Commit
41d5f70
·
verified ·
1 Parent(s): bceb9d9

Upload folder using huggingface_hub

Browse files
Files changed (47) hide show
  1. .gitattributes +3 -0
  2. chat_template.jinja +14 -0
  3. checkpoint-13500/chat_template.jinja +14 -0
  4. checkpoint-13500/config.json +74 -0
  5. checkpoint-13500/generation_config.json +6 -0
  6. checkpoint-13500/model-00001-of-00004.safetensors +3 -0
  7. checkpoint-13500/model-00002-of-00004.safetensors +3 -0
  8. checkpoint-13500/model-00003-of-00004.safetensors +3 -0
  9. checkpoint-13500/model-00004-of-00004.safetensors +3 -0
  10. checkpoint-13500/model.safetensors.index.json +407 -0
  11. checkpoint-13500/optimizer.pt +3 -0
  12. checkpoint-13500/rng_state.pth +3 -0
  13. checkpoint-13500/scheduler.pt +3 -0
  14. checkpoint-13500/special_tokens_map.json +17 -0
  15. checkpoint-13500/tokenizer.json +3 -0
  16. checkpoint-13500/tokenizer_config.json +249 -0
  17. checkpoint-13500/trainer_state.json +0 -0
  18. checkpoint-13500/training_args.bin +3 -0
  19. checkpoint-14000/chat_template.jinja +14 -0
  20. checkpoint-14000/config.json +74 -0
  21. checkpoint-14000/generation_config.json +6 -0
  22. checkpoint-14000/model-00001-of-00004.safetensors +3 -0
  23. checkpoint-14000/model-00002-of-00004.safetensors +3 -0
  24. checkpoint-14000/model-00003-of-00004.safetensors +3 -0
  25. checkpoint-14000/model-00004-of-00004.safetensors +3 -0
  26. checkpoint-14000/model.safetensors.index.json +407 -0
  27. checkpoint-14000/optimizer.pt +3 -0
  28. checkpoint-14000/rng_state.pth +3 -0
  29. checkpoint-14000/scheduler.pt +3 -0
  30. checkpoint-14000/special_tokens_map.json +17 -0
  31. checkpoint-14000/tokenizer.json +3 -0
  32. checkpoint-14000/tokenizer_config.json +249 -0
  33. checkpoint-14000/trainer_state.json +0 -0
  34. checkpoint-14000/training_args.bin +3 -0
  35. config.json +74 -0
  36. generation_config.json +6 -0
  37. model-00001-of-00004.safetensors +3 -0
  38. model-00002-of-00004.safetensors +3 -0
  39. model-00003-of-00004.safetensors +3 -0
  40. model-00004-of-00004.safetensors +3 -0
  41. model.safetensors.index.json +407 -0
  42. runs/Jul04_18-38-32_192-222-58-106/events.out.tfevents.1751654312.192-222-58-106.5871.0 +3 -0
  43. runs/Jul05_05-59-10_192-222-58-106/events.out.tfevents.1751695150.192-222-58-106.19459.0 +3 -0
  44. special_tokens_map.json +17 -0
  45. tokenizer.json +3 -0
  46. tokenizer_config.json +249 -0
  47. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-13500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-14000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
2
+
3
+ ' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
4
+ ' + '```json' + '
5
+ ' + tool['function']['arguments'] + '
6
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
7
+ ' + '```json' + '
8
+ ' + tool['function']['arguments'] + '
9
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
10
+ ' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
11
+ ' + '```json' + '
12
+ ' + tool['function']['arguments'] + '
13
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
14
+ <｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
checkpoint-13500/chat_template.jinja ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
2
+
3
+ ' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
4
+ ' + '```json' + '
5
+ ' + tool['function']['arguments'] + '
6
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
7
+ ' + '```json' + '
8
+ ' + tool['function']['arguments'] + '
9
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
10
+ ' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
11
+ ' + '```json' + '
12
+ ' + tool['function']['arguments'] + '
13
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
14
+ <｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
checkpoint-13500/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 131072,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151645,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": {
61
+ "attn_factor": 0.8782488562869419,
62
+ "factor": 4.0,
63
+ "original_max_position_embeddings": 32768,
64
+ "rope_type": "yarn"
65
+ },
66
+ "rope_theta": 1000000,
67
+ "sliding_window": null,
68
+ "tie_word_embeddings": false,
69
+ "torch_dtype": "bfloat16",
70
+ "transformers_version": "4.53.1",
71
+ "use_cache": true,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
checkpoint-13500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.53.1"
6
+ }
checkpoint-13500/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c07ffad6c11665bf62e35bbf5c34c2886c8bbc73472fb229cc2eae2cdcfe201
3
+ size 4902257696
checkpoint-13500/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43139982d7b44a613070b70034e2728e78d6a2d7283d9d1578e0ca1c8b16b7e8
3
+ size 4915960368
checkpoint-13500/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f1047b3d55d0ab2ea3152b47b932f232eb2c6b3086e7ecc8296c457acc7a32
3
+ size 4983068496
checkpoint-13500/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc68a0a33a377164f549581d639b767b22c7e5bd3a96b350efe66671613dd1f
3
+ size 1580230264
checkpoint-13500/model.safetensors.index.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8190735360,
4
+ "total_size": 16381470720
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
339
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
373
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
374
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
376
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
377
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
378
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
380
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
381
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
394
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
397
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
400
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
401
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
402
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
403
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
404
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
405
+ "model.norm.weight": "model-00004-of-00004.safetensors"
406
+ }
407
+ }
checkpoint-13500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b60502096e9fb22b549f66a5a3113f45775fe7a8022cba3a8d52b599abd09d7
3
+ size 32763290952
checkpoint-13500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
checkpoint-13500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc9ab27220f18ac863ac0f7ec7d8b748e7d6df43253d3874756d13bf36769abd
3
+ size 1465
checkpoint-13500/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<｜end▁of▁sentence｜>"
17
+ }
checkpoint-13500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5385e4dbcc5ad7e340249f938093cb4b35e9db582e85d7703faf969d6b2ba3
3
+ size 11423626
checkpoint-13500/tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜begin▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<｜end▁of▁sentence｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<tool_response>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "</tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<think>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "</think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<｜User｜>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "151670": {
223
+ "content": "<｜Assistant｜>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ }
230
+ },
231
+ "bos_token": "<｜begin▁of▁sentence｜>",
232
+ "clean_up_tokenization_spaces": false,
233
+ "eos_token": "<｜end▁of▁sentence｜>",
234
+ "extra_special_tokens": {},
235
+ "legacy": true,
236
+ "max_length": 2048,
237
+ "model_max_length": 131072,
238
+ "pad_to_multiple_of": null,
239
+ "pad_token": "<｜end▁of▁sentence｜>",
240
+ "pad_token_type_id": 0,
241
+ "padding_side": "left",
242
+ "sp_model_kwargs": {},
243
+ "stride": 0,
244
+ "tokenizer_class": "LlamaTokenizerFast",
245
+ "truncation_side": "right",
246
+ "truncation_strategy": "longest_first",
247
+ "unk_token": null,
248
+ "use_default_system_prompt": false
249
+ }
checkpoint-13500/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6079b4700c3127a593b34493925f68b0c6134c652e8a3e6ec669a6d7dc031836
3
+ size 5777
checkpoint-14000/chat_template.jinja ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '
2
+
3
+ ' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{% set content = message['content'] %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{%- set ns.is_first = false -%}{%- set ns.is_last_user = true -%}{{'<｜User｜>' + content + '<｜Assistant｜>'}}{%- endif %}{%- if message['role'] == 'assistant' %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{% endif %}{%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{%- endif %}{%- set ns.is_first = false %}{%- set ns.is_tool = false -%}{%- set ns.is_output_first = true %}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if content is none %}{{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
4
+ ' + '```json' + '
5
+ ' + tool['function']['arguments'] + '
6
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- else %}{{content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
7
+ ' + '```json' + '
8
+ ' + tool['function']['arguments'] + '
9
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'
10
+ ' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '
11
+ ' + '```json' + '
12
+ ' + tool['function']['arguments'] + '
13
+ ' + '```' + '<｜tool▁call▁end｜>'}}{%- endif %}{%- endfor %}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none)%}{%- set ns.is_last_user = false -%}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{{content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_last_user = false -%}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'
14
+ <｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_last_user and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}
checkpoint-14000/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 131072,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151645,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": {
61
+ "attn_factor": 0.8782488562869419,
62
+ "factor": 4.0,
63
+ "original_max_position_embeddings": 32768,
64
+ "rope_type": "yarn"
65
+ },
66
+ "rope_theta": 1000000,
67
+ "sliding_window": null,
68
+ "tie_word_embeddings": false,
69
+ "torch_dtype": "bfloat16",
70
+ "transformers_version": "4.53.1",
71
+ "use_cache": true,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
checkpoint-14000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.53.1"
6
+ }
checkpoint-14000/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c7e8f9c1af798b7eb98b5917750987787da72688933af3be4bffe7acbe5fbf
3
+ size 4902257696
checkpoint-14000/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9182cd0ef837f49dc94bfc9e70f97598987d168464870237e456e3b6ffc18e80
3
+ size 4915960368
checkpoint-14000/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8171443912b48e83258fb0728536ecd33c986887a78207bfcabc701ed72471df
3
+ size 4983068496
checkpoint-14000/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ca95f61f9700aa2db2b470114b174c9351e9da147f837b9e84e302ce5f3457
3
+ size 1580230264
checkpoint-14000/model.safetensors.index.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8190735360,
4
+ "total_size": 16381470720
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
339
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
373
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
374
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
376
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
377
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
378
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
380
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
381
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
394
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
397
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
400
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
401
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
402
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
403
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
404
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
405
+ "model.norm.weight": "model-00004-of-00004.safetensors"
406
+ }
407
+ }
checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e59e6d6a23aead8eae0236ab894fdad47a4a307bd42ccdfe487642581b2ab521
3
+ size 32763290952
checkpoint-14000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
3
+ size 14645
checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d6b555f23b8ab7ecea81189e9649b6e4d7e59d44863257b22bf56db17896ea7
3
+ size 1465
checkpoint-14000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<｜end▁of▁sentence｜>"
17
+ }
checkpoint-14000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5385e4dbcc5ad7e340249f938093cb4b35e9db582e85d7703faf969d6b2ba3
3
+ size 11423626
checkpoint-14000/tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜begin▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<｜end▁of▁sentence｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<tool_response>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "</tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<think>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "</think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<｜User｜>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "151670": {
223
+ "content": "<｜Assistant｜>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ }
230
+ },
231
+ "bos_token": "<｜begin▁of▁sentence｜>",
232
+ "clean_up_tokenization_spaces": false,
233
+ "eos_token": "<｜end▁of▁sentence｜>",
234
+ "extra_special_tokens": {},
235
+ "legacy": true,
236
+ "max_length": 2048,
237
+ "model_max_length": 131072,
238
+ "pad_to_multiple_of": null,
239
+ "pad_token": "<｜end▁of▁sentence｜>",
240
+ "pad_token_type_id": 0,
241
+ "padding_side": "left",
242
+ "sp_model_kwargs": {},
243
+ "stride": 0,
244
+ "tokenizer_class": "LlamaTokenizerFast",
245
+ "truncation_side": "right",
246
+ "truncation_strategy": "longest_first",
247
+ "unk_token": null,
248
+ "use_default_system_prompt": false
249
+ }
checkpoint-14000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6079b4700c3127a593b34493925f68b0c6134c652e8a3e6ec669a6d7dc031836
3
+ size 5777
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 12288,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 131072,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "pad_token_id": 151645,
59
+ "rms_norm_eps": 1e-06,
60
+ "rope_scaling": {
61
+ "attn_factor": 0.8782488562869419,
62
+ "factor": 4.0,
63
+ "original_max_position_embeddings": 32768,
64
+ "rope_type": "yarn"
65
+ },
66
+ "rope_theta": 1000000,
67
+ "sliding_window": null,
68
+ "tie_word_embeddings": false,
69
+ "torch_dtype": "bfloat16",
70
+ "transformers_version": "4.53.1",
71
+ "use_cache": true,
72
+ "use_sliding_window": false,
73
+ "vocab_size": 151936
74
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.53.1"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c7e8f9c1af798b7eb98b5917750987787da72688933af3be4bffe7acbe5fbf
3
+ size 4902257696
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9182cd0ef837f49dc94bfc9e70f97598987d168464870237e456e3b6ffc18e80
3
+ size 4915960368
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8171443912b48e83258fb0728536ecd33c986887a78207bfcabc701ed72471df
3
+ size 4983068496
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06ca95f61f9700aa2db2b470114b174c9351e9da147f837b9e84e302ce5f3457
3
+ size 1580230264
model.safetensors.index.json ADDED
@@ -0,0 +1,407 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8190735360,
4
+ "total_size": 16381470720
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
339
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
340
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
341
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
342
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
343
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
344
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
345
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
347
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
348
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
349
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
351
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
352
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
355
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
356
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
357
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
358
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
359
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
361
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
362
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
363
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
365
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
366
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
367
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
368
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
369
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
370
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
371
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
372
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
373
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
374
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
375
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
376
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
377
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
378
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
380
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
381
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
393
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
394
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
395
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
396
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
397
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
398
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
399
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
400
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
401
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
402
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
403
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
404
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
405
+ "model.norm.weight": "model-00004-of-00004.safetensors"
406
+ }
407
+ }
runs/Jul04_18-38-32_192-222-58-106/events.out.tfevents.1751654312.192-222-58-106.5871.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e318c2731ea6d22411387c20764ea82c68bc62c7359a639fb3c97d63b061a382
3
+ size 617927
runs/Jul05_05-59-10_192-222-58-106/events.out.tfevents.1751695150.192-222-58-106.19459.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be15c052cb73abae927c52e09507ede7edf21685b12aeed91a786d70245b6bf
3
+ size 301748
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<｜end▁of▁sentence｜>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5385e4dbcc5ad7e340249f938093cb4b35e9db582e85d7703faf969d6b2ba3
3
+ size 11423626
tokenizer_config.json ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<｜begin▁of▁sentence｜>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<｜end▁of▁sentence｜>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<tool_response>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "</tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<think>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "</think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<｜User｜>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "151670": {
223
+ "content": "<｜Assistant｜>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ }
230
+ },
231
+ "bos_token": "<｜begin▁of▁sentence｜>",
232
+ "clean_up_tokenization_spaces": false,
233
+ "eos_token": "<｜end▁of▁sentence｜>",
234
+ "extra_special_tokens": {},
235
+ "legacy": true,
236
+ "max_length": 2048,
237
+ "model_max_length": 131072,
238
+ "pad_to_multiple_of": null,
239
+ "pad_token": "<｜end▁of▁sentence｜>",
240
+ "pad_token_type_id": 0,
241
+ "padding_side": "left",
242
+ "sp_model_kwargs": {},
243
+ "stride": 0,
244
+ "tokenizer_class": "LlamaTokenizerFast",
245
+ "truncation_side": "right",
246
+ "truncation_strategy": "longest_first",
247
+ "unk_token": null,
248
+ "use_default_system_prompt": false
249
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6079b4700c3127a593b34493925f68b0c6134c652e8a3e6ec669a6d7dc031836
3
+ size 5777