Hugging Face's logo

hank0316
/
Qwen2.5-3B-Instruct-IE5

Safetensors
qwen2
Model card Files
xet
Community
hank0316 commited on
Commit
6ac66d5
·
verified ·
1 Parent(s): 4c1adee

Delete policy

Browse files
Files changed (13) hide show
  1. policy/added_tokens.json +0 -24
  2. policy/chat_template.jinja +0 -54
  3. policy/config.json +0 -67
  4. policy/generation_config.json +0 -14
  5. policy/merges.txt +0 -0
  6. policy/model-00001-of-00003.safetensors +0 -3
  7. policy/model-00002-of-00003.safetensors +0 -3
  8. policy/model-00003-of-00003.safetensors +0 -3
  9. policy/model.safetensors.index.json +0 -443
  10. policy/special_tokens_map.json +0 -31
  11. policy/tokenizer.json +0 -3
  12. policy/tokenizer_config.json +0 -207
  13. policy/vocab.json +0 -0
policy/added_tokens.json DELETED
@@ -1,24 +0,0 @@
1
- {
2
- "</tool_call>": 151658,
3
- "<tool_call>": 151657,
4
- "<|box_end|>": 151649,
5
- "<|box_start|>": 151648,
6
- "<|endoftext|>": 151643,
7
- "<|file_sep|>": 151664,
8
- "<|fim_middle|>": 151660,
9
- "<|fim_pad|>": 151662,
10
- "<|fim_prefix|>": 151659,
11
- "<|fim_suffix|>": 151661,
12
- "<|im_end|>": 151645,
13
- "<|im_start|>": 151644,
14
- "<|image_pad|>": 151655,
15
- "<|object_ref_end|>": 151647,
16
- "<|object_ref_start|>": 151646,
17
- "<|quad_end|>": 151651,
18
- "<|quad_start|>": 151650,
19
- "<|repo_name|>": 151663,
20
- "<|video_pad|>": 151656,
21
- "<|vision_end|>": 151653,
22
- "<|vision_pad|>": 151654,
23
- "<|vision_start|>": 151652
24
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/chat_template.jinja DELETED
@@ -1,54 +0,0 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0]['role'] == 'system' %}
4
- {{- messages[0]['content'] }}
5
- {%- else %}
6
- {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
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
- {%- else %}
18
- {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
- {%- endif %}
20
- {%- endif %}
21
- {%- for message in messages %}
22
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
- {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
- {%- elif message.role == "assistant" %}
25
- {{- '<|im_start|>' + message.role }}
26
- {%- if message.content %}
27
- {{- '\n' + message.content }}
28
- {%- endif %}
29
- {%- for tool_call in message.tool_calls %}
30
- {%- if tool_call.function is defined %}
31
- {%- set tool_call = tool_call.function %}
32
- {%- endif %}
33
- {{- '\n<tool_call>\n{"name": "' }}
34
- {{- tool_call.name }}
35
- {{- '", "arguments": ' }}
36
- {{- tool_call.arguments | tojson }}
37
- {{- '}\n</tool_call>' }}
38
- {%- endfor %}
39
- {{- '<|im_end|>\n' }}
40
- {%- elif message.role == "tool" %}
41
- {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
- {{- '<|im_start|>user' }}
43
- {%- endif %}
44
- {{- '\n<tool_response>\n' }}
45
- {{- message.content }}
46
- {{- '\n</tool_response>' }}
47
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
- {{- '<|im_end|>\n' }}
49
- {%- endif %}
50
- {%- endif %}
51
- {%- endfor %}
52
- {%- if add_generation_prompt %}
53
- {{- '<|im_start|>assistant\n' }}
54
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/config.json DELETED
@@ -1,67 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151645,
8
- "hidden_act": "silu",
9
- "hidden_size": 2048,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 11008,
12
- "layer_types": [
13
- "full_attention",
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
- ],
50
- "max_position_embeddings": 32768,
51
- "max_window_layers": 70,
52
- "model_type": "qwen2",
53
- "num_attention_heads": 16,
54
- "num_hidden_layers": 36,
55
- "num_key_value_heads": 2,
56
- "pad_token_id": 151643,
57
- "rms_norm_eps": 1e-06,
58
- "rope_scaling": null,
59
- "rope_theta": 1000000.0,
60
- "sliding_window": null,
61
- "tie_word_embeddings": true,
62
- "torch_dtype": "float32",
63
- "transformers_version": "4.53.0",
64
- "use_cache": false,
65
- "use_sliding_window": false,
66
- "vocab_size": 151936
67
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.05,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "4.53.0"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
policy/model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e36e4f2c4e2cbdb79429ae970f29a90cee674c3a2fd50c4d8077ded8ef1b10f
3
- size 4982131536
 
 
 
 
policy/model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ca9bc7de791fb6a5cc923a044d67ef5a642cb927684f850c1a95dfab8994f3c
3
- size 4932949336
 
 
 
 
policy/model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bf408a1ef7ef3e11ede7db42b8e2c05aa0e9f80920aa8329e593e8bc412e26a
3
- size 3673383040
 
 
 
 
policy/model.safetensors.index.json DELETED
@@ -1,443 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 3085938688,
4
- "total_size": 13588414464
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00003-of-00003.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
18
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
20
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
27
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
28
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
30
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
31
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
32
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
36
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
37
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
38
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
39
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
40
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
41
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
42
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
44
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
45
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
46
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
47
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
48
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
49
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
50
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
51
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
52
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
53
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
54
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
55
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
56
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
57
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
63
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
64
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
65
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
66
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
67
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
68
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
69
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
75
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
78
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
80
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
87
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
90
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
92
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
99
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
102
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
104
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
111
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
114
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
116
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
117
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
118
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
119
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
120
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
121
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
122
- "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
123
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
124
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
125
- "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
126
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
128
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
135
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
138
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
140
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
144
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
145
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
146
- "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
147
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
148
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
150
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
152
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
153
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
154
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
155
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
156
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
157
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
158
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
159
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
160
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
161
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
162
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
163
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
164
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
165
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
166
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
167
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
168
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
169
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
170
- "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
171
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
172
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
173
- "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
174
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
175
- "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
176
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
177
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
178
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
179
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
180
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
181
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
182
- "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
183
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
184
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
185
- "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
186
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
- "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
188
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
189
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
190
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
191
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
192
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
193
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
194
- "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
195
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
196
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
197
- "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
198
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
199
- "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
200
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
201
- "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
202
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
203
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
204
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
205
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
206
- "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
207
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
208
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
209
- "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
210
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
211
- "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
212
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
213
- "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
214
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
215
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
216
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
217
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
218
- "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
219
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
220
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
221
- "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
222
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
223
- "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
224
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
225
- "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
226
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
227
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
228
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
229
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
230
- "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
231
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
232
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
233
- "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
234
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
235
- "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
236
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
237
- "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
238
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
239
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
240
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
241
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
242
- "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
243
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
244
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
245
- "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
246
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
247
- "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
248
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
249
- "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
250
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
251
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
252
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
253
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
254
- "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
255
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
256
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
257
- "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
258
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
259
- "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
260
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
261
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
262
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
263
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
264
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
265
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
266
- "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
267
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
268
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
269
- "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
270
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
271
- "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
272
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
273
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
274
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
275
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
276
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
277
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
278
- "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
279
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
280
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
281
- "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
282
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
283
- "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
284
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
285
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
291
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
294
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
296
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
297
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
298
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
299
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
300
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
301
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
302
- "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
303
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
304
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
305
- "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
306
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
307
- "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
308
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
309
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
310
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
311
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
312
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
313
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
314
- "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
315
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
316
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
317
- "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
318
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
319
- "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
320
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
321
- "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
322
- "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
323
- "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
324
- "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
325
- "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
326
- "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
327
- "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
328
- "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
329
- "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
330
- "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
331
- "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
332
- "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
333
- "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
334
- "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
335
- "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
336
- "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
337
- "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
338
- "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
339
- "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
340
- "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
341
- "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
342
- "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
343
- "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
344
- "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
345
- "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
346
- "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
347
- "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
348
- "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
349
- "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
350
- "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
351
- "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
352
- "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
353
- "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
354
- "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
355
- "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
356
- "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
357
- "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
358
- "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
359
- "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
360
- "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
361
- "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
362
- "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
363
- "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
364
- "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
365
- "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
366
- "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
367
- "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
368
- "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
369
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
370
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
371
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
372
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
373
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
374
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
375
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
376
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
377
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
378
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
379
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
380
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
381
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
382
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
383
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
384
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
385
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
386
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
387
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
388
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
389
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
390
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
391
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
392
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
393
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
394
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
395
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
396
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
397
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
398
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
399
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
400
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
401
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
402
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
403
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
404
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
405
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
406
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
407
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
408
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
409
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
410
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
411
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
412
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
413
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
414
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
415
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
416
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
417
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
418
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
419
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
420
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
421
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
422
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
423
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
424
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
425
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
426
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
427
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
428
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
429
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
430
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
431
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
432
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
433
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
434
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
435
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
436
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
437
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
438
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
439
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
440
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
441
- "model.norm.weight": "model-00003-of-00003.safetensors"
442
- }
443
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
 
 
 
policy/tokenizer_config.json DELETED
@@ -1,207 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- }
181
- },
182
- "additional_special_tokens": [
183
- "<|im_start|>",
184
- "<|im_end|>",
185
- "<|object_ref_start|>",
186
- "<|object_ref_end|>",
187
- "<|box_start|>",
188
- "<|box_end|>",
189
- "<|quad_start|>",
190
- "<|quad_end|>",
191
- "<|vision_start|>",
192
- "<|vision_end|>",
193
- "<|vision_pad|>",
194
- "<|image_pad|>",
195
- "<|video_pad|>"
196
- ],
197
- "bos_token": null,
198
- "clean_up_tokenization_spaces": false,
199
- "eos_token": "<|im_end|>",
200
- "errors": "replace",
201
- "extra_special_tokens": {},
202
- "model_max_length": 131072,
203
- "pad_token": "<|endoftext|>",
204
- "split_special_tokens": false,
205
- "tokenizer_class": "Qwen2Tokenizer",
206
- "unk_token": null
207
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
policy/vocab.json DELETED
The diff for this file is too large to render. See raw diff