Hugging Face's logo

eth-sri
/
kodcode-v1-qwq-secureplusplus

Safetensors
qwen2
🇪🇺 Region: EU
Model card Files
xet
 Community
moogician commited on
Commit
db3a986
·
verified ·
1 Parent(s): a3c8300

Upload kodcode-v1-qwq-secureplusplus

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +62 -0
  3. config.json +97 -0
  4. generation_config.json +13 -0
  5. model-00001-of-00002.safetensors +3 -0
  6. model-00002-of-00002.safetensors +3 -0
  7. model.safetensors.index.json +779 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +31 -0
  10. trainer_state.json +622 -0
  11. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- '' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- endif %}
18
+ {%- endif %}
19
+ {%- for message in messages %}
20
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
21
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
22
+ {%- elif message.role == "assistant" and not message.tool_calls %}
23
+ {%- set content = message.content %}
24
+ {%- if not loop.last %}
25
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
26
+ {%- endif %}
27
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
28
+ {%- elif message.role == "assistant" %}
29
+ {%- set content = message.content %}
30
+ {%- if not loop.last %}
31
+ {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
32
+ {%- endif %}
33
+ {{- '<|im_start|>' + message.role }}
34
+ {%- if message.content %}
35
+ {{- '\n' + content }}
36
+ {%- endif %}
37
+ {%- for tool_call in message.tool_calls %}
38
+ {%- if tool_call.function is defined %}
39
+ {%- set tool_call = tool_call.function %}
40
+ {%- endif %}
41
+ {{- '\n<tool_call>\n{"name": "' }}
42
+ {{- tool_call.name }}
43
+ {{- '", "arguments": ' }}
44
+ {{- tool_call.arguments | tojson }}
45
+ {{- '}\n</tool_call>' }}
46
+ {%- endfor %}
47
+ {{- '<|im_end|>\n' }}
48
+ {%- elif message.role == "tool" %}
49
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
50
+ {{- '<|im_start|>user' }}
51
+ {%- endif %}
52
+ {{- '\n<tool_response>\n' }}
53
+ {{- message.content }}
54
+ {{- '\n</tool_response>' }}
55
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
56
+ {{- '<|im_end|>\n' }}
57
+ {%- endif %}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- if add_generation_prompt %}
61
+ {{- '<|im_start|>assistant\n<think>\n' }}
62
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "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
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention"
78
+ ],
79
+ "max_position_embeddings": 40960,
80
+ "max_window_layers": 64,
81
+ "model_type": "qwen2",
82
+ "num_attention_heads": 40,
83
+ "num_hidden_layers": 64,
84
+ "num_key_value_heads": 8,
85
+ "pad_token_id": 151643,
86
+ "rms_norm_eps": 1e-05,
87
+ "rope_parameters": {
88
+ "rope_theta": 1000000.0,
89
+ "rope_type": "default"
90
+ },
91
+ "sliding_window": null,
92
+ "tie_word_embeddings": false,
93
+ "transformers_version": "5.6.0",
94
+ "use_cache": false,
95
+ "use_sliding_window": false,
96
+ "vocab_size": 152064
97
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.0,
9
+ "temperature": 0.6,
10
+ "top_k": 40,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.6.0"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d582910623125ff28a891d806c9fb02554da3fe228354b2b956d6ec715b0bbb
3
+ size 49924452408
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18b6e4c03d7838ceaabf696517db642b1e6f75cd165b23a15c8a294f284daf1
3
+ size 15603390216
model.safetensors.index.json ADDED
@@ -0,0 +1,779 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 1119232,
4
+ "total_size": 65527752704
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
267
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
270
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
272
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
279
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
282
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
284
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
296
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
303
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
306
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
308
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
315
+ "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
318
+ "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
320
+ "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
327
+ "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
+ "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
+ "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
336
+ "model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
337
+ "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
339
+ "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
342
+ "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
344
+ "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
351
+ "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
354
+ "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
356
+ "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
363
+ "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
366
+ "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
368
+ "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
375
+ "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
380
+ "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
387
+ "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
392
+ "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
399
+ "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
404
+ "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
411
+ "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
423
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
435
+ "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
440
+ "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.41.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
447
+ "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.41.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
450
+ "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.41.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
452
+ "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
458
+ "model.layers.42.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
459
+ "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.42.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
462
+ "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.42.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
464
+ "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
469
+ "model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.43.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
471
+ "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
472
+ "model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
473
+ "model.layers.43.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
474
+ "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
475
+ "model.layers.43.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
476
+ "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
477
+ "model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
478
+ "model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
481
+ "model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
482
+ "model.layers.44.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
483
+ "model.layers.44.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
484
+ "model.layers.44.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
485
+ "model.layers.44.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
486
+ "model.layers.44.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
487
+ "model.layers.44.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
488
+ "model.layers.44.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
490
+ "model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
492
+ "model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
493
+ "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
494
+ "model.layers.45.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
495
+ "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
496
+ "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
497
+ "model.layers.45.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
498
+ "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
499
+ "model.layers.45.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
500
+ "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
501
+ "model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
502
+ "model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
504
+ "model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
505
+ "model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
506
+ "model.layers.46.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
507
+ "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
508
+ "model.layers.46.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
509
+ "model.layers.46.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
510
+ "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
511
+ "model.layers.46.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
512
+ "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
513
+ "model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors",
514
+ "model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
515
+ "model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
516
+ "model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
517
+ "model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
518
+ "model.layers.47.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
519
+ "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
520
+ "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
521
+ "model.layers.47.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
522
+ "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
523
+ "model.layers.47.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
524
+ "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
525
+ "model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
526
+ "model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
527
+ "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
528
+ "model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
529
+ "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
530
+ "model.layers.48.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
531
+ "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
532
+ "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
533
+ "model.layers.48.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
534
+ "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
535
+ "model.layers.48.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
536
+ "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
537
+ "model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
538
+ "model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
539
+ "model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
540
+ "model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
541
+ "model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
542
+ "model.layers.49.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
543
+ "model.layers.49.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
544
+ "model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
545
+ "model.layers.49.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
546
+ "model.layers.49.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
547
+ "model.layers.49.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
548
+ "model.layers.49.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
549
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
550
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
552
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
553
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
554
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
555
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
556
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
557
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
558
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
559
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
560
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
561
+ "model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
562
+ "model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
563
+ "model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
564
+ "model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
565
+ "model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
566
+ "model.layers.50.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
567
+ "model.layers.50.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
568
+ "model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
569
+ "model.layers.50.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
570
+ "model.layers.50.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
571
+ "model.layers.50.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
572
+ "model.layers.50.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
573
+ "model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
574
+ "model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
575
+ "model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
576
+ "model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
577
+ "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
578
+ "model.layers.51.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
579
+ "model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
580
+ "model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
581
+ "model.layers.51.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
582
+ "model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
583
+ "model.layers.51.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
584
+ "model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
585
+ "model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
586
+ "model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
587
+ "model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
588
+ "model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
589
+ "model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
590
+ "model.layers.52.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
591
+ "model.layers.52.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
592
+ "model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
593
+ "model.layers.52.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
594
+ "model.layers.52.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
595
+ "model.layers.52.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
596
+ "model.layers.52.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
597
+ "model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
598
+ "model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
599
+ "model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
600
+ "model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
601
+ "model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
602
+ "model.layers.53.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
603
+ "model.layers.53.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
604
+ "model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
605
+ "model.layers.53.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
606
+ "model.layers.53.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
607
+ "model.layers.53.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
608
+ "model.layers.53.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
609
+ "model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors",
610
+ "model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
611
+ "model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
612
+ "model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
613
+ "model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
614
+ "model.layers.54.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
615
+ "model.layers.54.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
616
+ "model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
617
+ "model.layers.54.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
618
+ "model.layers.54.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
619
+ "model.layers.54.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
620
+ "model.layers.54.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
621
+ "model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors",
622
+ "model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
623
+ "model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
624
+ "model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
625
+ "model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
626
+ "model.layers.55.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
627
+ "model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
628
+ "model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
629
+ "model.layers.55.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
630
+ "model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
631
+ "model.layers.55.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
632
+ "model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
633
+ "model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors",
634
+ "model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
635
+ "model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
636
+ "model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
637
+ "model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
638
+ "model.layers.56.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
639
+ "model.layers.56.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
640
+ "model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
641
+ "model.layers.56.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
642
+ "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
643
+ "model.layers.56.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
644
+ "model.layers.56.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
645
+ "model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors",
646
+ "model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
647
+ "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
648
+ "model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
649
+ "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
650
+ "model.layers.57.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
651
+ "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
652
+ "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
653
+ "model.layers.57.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
654
+ "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
655
+ "model.layers.57.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
656
+ "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
657
+ "model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors",
658
+ "model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
659
+ "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
660
+ "model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
661
+ "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
662
+ "model.layers.58.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
663
+ "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
664
+ "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
665
+ "model.layers.58.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
666
+ "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
667
+ "model.layers.58.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
668
+ "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
669
+ "model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors",
670
+ "model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
671
+ "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
672
+ "model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
673
+ "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
674
+ "model.layers.59.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
675
+ "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
676
+ "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
677
+ "model.layers.59.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
678
+ "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
679
+ "model.layers.59.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
680
+ "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
681
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
682
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
683
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
684
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
685
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
686
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
687
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
688
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
689
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
690
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
691
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
692
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
693
+ "model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors",
694
+ "model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
695
+ "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
696
+ "model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
697
+ "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
698
+ "model.layers.60.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
699
+ "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
700
+ "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
701
+ "model.layers.60.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
702
+ "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
703
+ "model.layers.60.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
704
+ "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
705
+ "model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors",
706
+ "model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
707
+ "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
708
+ "model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
709
+ "model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
710
+ "model.layers.61.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
711
+ "model.layers.61.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
712
+ "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
713
+ "model.layers.61.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
714
+ "model.layers.61.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
715
+ "model.layers.61.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
716
+ "model.layers.61.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
717
+ "model.layers.62.input_layernorm.weight": "model-00002-of-00002.safetensors",
718
+ "model.layers.62.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
719
+ "model.layers.62.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
720
+ "model.layers.62.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
721
+ "model.layers.62.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
722
+ "model.layers.62.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
723
+ "model.layers.62.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
724
+ "model.layers.62.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
725
+ "model.layers.62.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
726
+ "model.layers.62.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
727
+ "model.layers.62.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
728
+ "model.layers.62.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
729
+ "model.layers.63.input_layernorm.weight": "model-00002-of-00002.safetensors",
730
+ "model.layers.63.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
731
+ "model.layers.63.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
732
+ "model.layers.63.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
733
+ "model.layers.63.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
734
+ "model.layers.63.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
735
+ "model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
736
+ "model.layers.63.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
737
+ "model.layers.63.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
738
+ "model.layers.63.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
739
+ "model.layers.63.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
740
+ "model.layers.63.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
741
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
742
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
743
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
744
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
745
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
746
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
747
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
748
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
749
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
750
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
751
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
752
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
753
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
754
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
755
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
756
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
757
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
758
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
759
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
760
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
761
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
762
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
763
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
764
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
765
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
766
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
767
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
768
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
769
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
770
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
771
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
772
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
773
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
774
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
775
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
776
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
777
+ "model.norm.weight": "model-00002-of-00002.safetensors"
778
+ }
779
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "padding_side": "right",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null
31
+ }
trainer_state.json ADDED
@@ -0,0 +1,622 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 84,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03614457831325301,
14
+ "grad_norm": 3.5530667304992676,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.8157972693443298,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07228915662650602,
21
+ "grad_norm": 3.475752353668213,
22
+ "learning_rate": 1.111111111111111e-06,
23
+ "loss": 0.8220954537391663,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.10843373493975904,
28
+ "grad_norm": 3.383586883544922,
29
+ "learning_rate": 2.222222222222222e-06,
30
+ "loss": 0.8105647563934326,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.14457831325301204,
35
+ "grad_norm": 3.3059158325195312,
36
+ "learning_rate": 3.3333333333333333e-06,
37
+ "loss": 0.7966299057006836,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.18072289156626506,
42
+ "grad_norm": 2.887650728225708,
43
+ "learning_rate": 4.444444444444444e-06,
44
+ "loss": 0.7848972082138062,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.21686746987951808,
49
+ "grad_norm": 2.0149731636047363,
50
+ "learning_rate": 5.555555555555557e-06,
51
+ "loss": 0.7373118996620178,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.25301204819277107,
56
+ "grad_norm": 1.521030068397522,
57
+ "learning_rate": 6.666666666666667e-06,
58
+ "loss": 0.7128340601921082,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.2891566265060241,
63
+ "grad_norm": 1.3453000783920288,
64
+ "learning_rate": 7.77777777777778e-06,
65
+ "loss": 0.706008791923523,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.3253012048192771,
70
+ "grad_norm": 1.3435814380645752,
71
+ "learning_rate": 8.888888888888888e-06,
72
+ "loss": 0.7266546487808228,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.3614457831325301,
77
+ "grad_norm": 2.6775221824645996,
78
+ "learning_rate": 1e-05,
79
+ "loss": 0.7641190886497498,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.39759036144578314,
84
+ "grad_norm": 2.31797456741333,
85
+ "learning_rate": 9.995614150494293e-06,
86
+ "loss": 0.7511537075042725,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.43373493975903615,
91
+ "grad_norm": 1.8419780731201172,
92
+ "learning_rate": 9.982464296247523e-06,
93
+ "loss": 0.725541353225708,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.46987951807228917,
98
+ "grad_norm": 1.5448116064071655,
99
+ "learning_rate": 9.960573506572391e-06,
100
+ "loss": 0.7165950536727905,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.5060240963855421,
105
+ "grad_norm": 1.3775088787078857,
106
+ "learning_rate": 9.929980185352525e-06,
107
+ "loss": 0.7150700688362122,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.5421686746987951,
112
+ "grad_norm": 1.2375344038009644,
113
+ "learning_rate": 9.890738003669029e-06,
114
+ "loss": 0.7106208801269531,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.5783132530120482,
119
+ "grad_norm": 1.0106751918792725,
120
+ "learning_rate": 9.842915805643156e-06,
121
+ "loss": 0.6804662942886353,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.6144578313253012,
126
+ "grad_norm": 1.026816487312317,
127
+ "learning_rate": 9.786597487660336e-06,
128
+ "loss": 0.6793582439422607,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.6506024096385542,
133
+ "grad_norm": 0.960710346698761,
134
+ "learning_rate": 9.721881851187406e-06,
135
+ "loss": 0.6606736779212952,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.6867469879518072,
140
+ "grad_norm": 0.8846614956855774,
141
+ "learning_rate": 9.648882429441258e-06,
142
+ "loss": 0.6600944399833679,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.7228915662650602,
147
+ "grad_norm": 0.7778003215789795,
148
+ "learning_rate": 9.567727288213005e-06,
149
+ "loss": 0.6360255479812622,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.7590361445783133,
154
+ "grad_norm": 0.7867444157600403,
155
+ "learning_rate": 9.478558801197065e-06,
156
+ "loss": 0.6492308378219604,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.7951807228915663,
161
+ "grad_norm": 0.9391480684280396,
162
+ "learning_rate": 9.381533400219319e-06,
163
+ "loss": 0.6748710870742798,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.8313253012048193,
168
+ "grad_norm": 0.7031015157699585,
169
+ "learning_rate": 9.276821300802535e-06,
170
+ "loss": 0.6428183913230896,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.8674698795180723,
175
+ "grad_norm": 0.6937193274497986,
176
+ "learning_rate": 9.164606203550498e-06,
177
+ "loss": 0.6585266590118408,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.9036144578313253,
182
+ "grad_norm": 0.6111941933631897,
183
+ "learning_rate": 9.045084971874738e-06,
184
+ "loss": 0.6351627111434937,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.9397590361445783,
189
+ "grad_norm": 0.6165474653244019,
190
+ "learning_rate": 8.9184672866292e-06,
191
+ "loss": 0.6526360511779785,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.9759036144578314,
196
+ "grad_norm": 0.5291957855224609,
197
+ "learning_rate": 8.784975278258783e-06,
198
+ "loss": 0.6265251636505127,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 1.0,
203
+ "grad_norm": 0.6292035579681396,
204
+ "learning_rate": 8.644843137107058e-06,
205
+ "loss": 0.6393284797668457,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 1.036144578313253,
210
+ "grad_norm": 0.5975921750068665,
211
+ "learning_rate": 8.498316702566828e-06,
212
+ "loss": 0.5895029306411743,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 1.072289156626506,
217
+ "grad_norm": 0.5670790672302246,
218
+ "learning_rate": 8.345653031794292e-06,
219
+ "loss": 0.5864728093147278,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 1.108433734939759,
224
+ "grad_norm": 0.7133178114891052,
225
+ "learning_rate": 8.18711994874345e-06,
226
+ "loss": 0.5745179653167725,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 1.144578313253012,
231
+ "grad_norm": 0.5750840306282043,
232
+ "learning_rate": 8.022995574311876e-06,
233
+ "loss": 0.5763933658599854,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 1.180722891566265,
238
+ "grad_norm": 0.5429960489273071,
239
+ "learning_rate": 7.85356783842216e-06,
240
+ "loss": 0.5829252600669861,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 1.216867469879518,
245
+ "grad_norm": 0.5182336568832397,
246
+ "learning_rate": 7.679133974894984e-06,
247
+ "loss": 0.5825693011283875,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 1.2530120481927711,
252
+ "grad_norm": 0.5491313934326172,
253
+ "learning_rate": 7.500000000000001e-06,
254
+ "loss": 0.5764566659927368,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 1.2891566265060241,
259
+ "grad_norm": 0.5254521369934082,
260
+ "learning_rate": 7.31648017559931e-06,
261
+ "loss": 0.5880482792854309,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 1.3253012048192772,
266
+ "grad_norm": 0.5171566009521484,
267
+ "learning_rate": 7.128896457825364e-06,
268
+ "loss": 0.6008750200271606,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.3614457831325302,
273
+ "grad_norm": 0.46462559700012207,
274
+ "learning_rate": 6.9375779322605154e-06,
275
+ "loss": 0.5682947635650635,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.3975903614457832,
280
+ "grad_norm": 0.5075864791870117,
281
+ "learning_rate": 6.7428602366090764e-06,
282
+ "loss": 0.5605165362358093,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.4337349397590362,
287
+ "grad_norm": 0.49260249733924866,
288
+ "learning_rate": 6.545084971874738e-06,
289
+ "loss": 0.5598280429840088,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.4698795180722892,
294
+ "grad_norm": 0.4913742244243622,
295
+ "learning_rate": 6.344599103076329e-06,
296
+ "loss": 0.5590924024581909,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.5060240963855422,
301
+ "grad_norm": 0.43512162566185,
302
+ "learning_rate": 6.141754350553279e-06,
303
+ "loss": 0.5489959716796875,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.5421686746987953,
308
+ "grad_norm": 0.46241137385368347,
309
+ "learning_rate": 5.936906572928625e-06,
310
+ "loss": 0.5644493103027344,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 1.5783132530120483,
315
+ "grad_norm": 0.43606171011924744,
316
+ "learning_rate": 5.730415142812059e-06,
317
+ "loss": 0.5436263084411621,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 1.6144578313253013,
322
+ "grad_norm": 0.5366220474243164,
323
+ "learning_rate": 5.522642316338268e-06,
324
+ "loss": 0.5769392251968384,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 1.6506024096385543,
329
+ "grad_norm": 0.5427200794219971,
330
+ "learning_rate": 5.3139525976465675e-06,
331
+ "loss": 0.5742834210395813,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 1.6867469879518073,
336
+ "grad_norm": 0.4113039970397949,
337
+ "learning_rate": 5.1047120994167855e-06,
338
+ "loss": 0.5463815927505493,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 1.7228915662650603,
343
+ "grad_norm": 0.44332143664360046,
344
+ "learning_rate": 4.895287900583216e-06,
345
+ "loss": 0.572960615158081,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 1.7590361445783134,
350
+ "grad_norm": 0.4870039224624634,
351
+ "learning_rate": 4.686047402353433e-06,
352
+ "loss": 0.5843434929847717,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.7951807228915664,
357
+ "grad_norm": 0.44245144724845886,
358
+ "learning_rate": 4.477357683661734e-06,
359
+ "loss": 0.5725433230400085,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.8313253012048194,
364
+ "grad_norm": 0.43352383375167847,
365
+ "learning_rate": 4.269584857187942e-06,
366
+ "loss": 0.55963134765625,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.8674698795180724,
371
+ "grad_norm": 0.45807719230651855,
372
+ "learning_rate": 4.063093427071376e-06,
373
+ "loss": 0.5634369850158691,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.9036144578313254,
378
+ "grad_norm": 0.4268049895763397,
379
+ "learning_rate": 3.8582456494467214e-06,
380
+ "loss": 0.582618772983551,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.9397590361445785,
385
+ "grad_norm": 0.4014423191547394,
386
+ "learning_rate": 3.655400896923672e-06,
387
+ "loss": 0.5639011859893799,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.9759036144578315,
392
+ "grad_norm": 0.4203037917613983,
393
+ "learning_rate": 3.4549150281252635e-06,
394
+ "loss": 0.5671670436859131,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 2.0,
399
+ "grad_norm": 0.5056357979774475,
400
+ "learning_rate": 3.2571397633909252e-06,
401
+ "loss": 0.5666017532348633,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 2.036144578313253,
406
+ "grad_norm": 0.42152824997901917,
407
+ "learning_rate": 3.0624220677394854e-06,
408
+ "loss": 0.5147315263748169,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 2.072289156626506,
413
+ "grad_norm": 0.4358435273170471,
414
+ "learning_rate": 2.871103542174637e-06,
415
+ "loss": 0.5106508731842041,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 2.108433734939759,
420
+ "grad_norm": 0.4385116994380951,
421
+ "learning_rate": 2.683519824400693e-06,
422
+ "loss": 0.5132982134819031,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 2.144578313253012,
427
+ "grad_norm": 0.42670226097106934,
428
+ "learning_rate": 2.5000000000000015e-06,
429
+ "loss": 0.504179060459137,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 2.180722891566265,
434
+ "grad_norm": 0.48987889289855957,
435
+ "learning_rate": 2.320866025105016e-06,
436
+ "loss": 0.5210374593734741,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 2.216867469879518,
441
+ "grad_norm": 0.4328784942626953,
442
+ "learning_rate": 2.146432161577842e-06,
443
+ "loss": 0.5118027925491333,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 2.253012048192771,
448
+ "grad_norm": 0.3858642578125,
449
+ "learning_rate": 1.977004425688126e-06,
450
+ "loss": 0.4922132194042206,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 2.289156626506024,
455
+ "grad_norm": 0.38921093940734863,
456
+ "learning_rate": 1.8128800512565514e-06,
457
+ "loss": 0.501984715461731,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 2.325301204819277,
462
+ "grad_norm": 0.3826121389865875,
463
+ "learning_rate": 1.6543469682057105e-06,
464
+ "loss": 0.5015629529953003,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 2.36144578313253,
469
+ "grad_norm": 0.40731289982795715,
470
+ "learning_rate": 1.5016832974331725e-06,
471
+ "loss": 0.5080351829528809,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 2.397590361445783,
476
+ "grad_norm": 0.3691997826099396,
477
+ "learning_rate": 1.3551568628929434e-06,
478
+ "loss": 0.5081236362457275,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 2.433734939759036,
483
+ "grad_norm": 0.3707135319709778,
484
+ "learning_rate": 1.2150247217412186e-06,
485
+ "loss": 0.5000795125961304,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 2.4698795180722892,
490
+ "grad_norm": 0.4231833517551422,
491
+ "learning_rate": 1.0815327133708015e-06,
492
+ "loss": 0.489562064409256,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 2.5060240963855422,
497
+ "grad_norm": 0.44199568033218384,
498
+ "learning_rate": 9.549150281252633e-07,
499
+ "loss": 0.5084055066108704,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 2.5421686746987953,
504
+ "grad_norm": 0.3709920048713684,
505
+ "learning_rate": 8.353937964495029e-07,
506
+ "loss": 0.5084290504455566,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 2.5783132530120483,
511
+ "grad_norm": 0.39795491099357605,
512
+ "learning_rate": 7.23178699197467e-07,
513
+ "loss": 0.513380229473114,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 2.6144578313253013,
518
+ "grad_norm": 0.36789605021476746,
519
+ "learning_rate": 6.184665997806832e-07,
520
+ "loss": 0.47666290402412415,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 2.6506024096385543,
525
+ "grad_norm": 0.38667839765548706,
526
+ "learning_rate": 5.214411988029355e-07,
527
+ "loss": 0.4979460835456848,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 2.6867469879518073,
532
+ "grad_norm": 0.5737469792366028,
533
+ "learning_rate": 4.322727117869951e-07,
534
+ "loss": 0.5057819485664368,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 2.7228915662650603,
539
+ "grad_norm": 0.4119950234889984,
540
+ "learning_rate": 3.511175705587433e-07,
541
+ "loss": 0.4980058968067169,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 2.7590361445783134,
546
+ "grad_norm": 0.38781502842903137,
547
+ "learning_rate": 2.7811814881259503e-07,
548
+ "loss": 0.5025761723518372,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 2.7951807228915664,
553
+ "grad_norm": 0.394298255443573,
554
+ "learning_rate": 2.134025123396638e-07,
555
+ "loss": 0.4871373176574707,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 2.8313253012048194,
560
+ "grad_norm": 0.34674161672592163,
561
+ "learning_rate": 1.5708419435684463e-07,
562
+ "loss": 0.5203001499176025,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 2.8674698795180724,
567
+ "grad_norm": 0.3848899006843567,
568
+ "learning_rate": 1.0926199633097156e-07,
569
+ "loss": 0.4973796010017395,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 2.9036144578313254,
574
+ "grad_norm": 0.3862093985080719,
575
+ "learning_rate": 7.001981464747565e-08,
576
+ "loss": 0.5090079307556152,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 2.9397590361445785,
581
+ "grad_norm": 0.39008447527885437,
582
+ "learning_rate": 3.9426493427611177e-08,
583
+ "loss": 0.5036866068840027,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 2.9759036144578315,
588
+ "grad_norm": 0.3627244830131531,
589
+ "learning_rate": 1.753570375247815e-08,
590
+ "loss": 0.5087746977806091,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 3.0,
595
+ "grad_norm": 0.4105032980442047,
596
+ "learning_rate": 4.385849505708084e-09,
597
+ "loss": 0.5212332010269165,
598
+ "step": 84
599
+ }
600
+ ],
601
+ "logging_steps": 1,
602
+ "max_steps": 84,
603
+ "num_input_tokens_seen": 0,
604
+ "num_train_epochs": 3,
605
+ "save_steps": 100000,
606
+ "stateful_callbacks": {
607
+ "TrainerControl": {
608
+ "args": {
609
+ "should_epoch_stop": false,
610
+ "should_evaluate": false,
611
+ "should_log": false,
612
+ "should_save": true,
613
+ "should_training_stop": true
614
+ },
615
+ "attributes": {}
616
+ }
617
+ },
618
+ "total_flos": 105954970763264.0,
619
+ "train_batch_size": 1,
620
+ "trial_name": null,
621
+ "trial_params": null
622
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbe7101a2108fbcdced44942107473c512c22a9f1347425760963be7fd43317
3
+ size 7953