Hugging Face's logo

cminst
/
AutoDeco-R1-Distill-Qwen-7B-Merged

Safetensors
autodeco
Model card Files
xet
Community
qingy2024 commited on
Commit
56d3e79
·
verified ·
1 Parent(s): 2bac4a9

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. .ipynb_checkpoints/chat_template-checkpoint.jinja +65 -0
  2. .ipynb_checkpoints/config-checkpoint.json +66 -0
  3. chat_template.jinja +65 -0
  4. config.json +66 -0
  5. generation_config.json +9 -0
  6. model-00001-of-000002.safetensors +3 -0
  7. model-00002-of-000002.safetensors +3 -0
  8. model.safetensors.index.json +354 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +35 -0
.ipynb_checkpoints/chat_template-checkpoint.jinja ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if not add_generation_prompt is defined -%}
2
+ {%- set add_generation_prompt = false -%}
3
+ {%- endif -%}
4
+ {%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt="") -%}
5
+ {%- for message in messages -%}
6
+ {%- if message["role"] == "system" -%}
7
+ {%- set ns.system_prompt = message["content"] -%}
8
+ {%- endif -%}
9
+ {%- endfor -%}
10
+ {{- bos_token -}}
11
+ {{- ns.system_prompt -}}
12
+ {%- for message in messages -%}
13
+ {%- if message["role"] == "user" -%}
14
+ {%- set ns.is_tool = false -%}
15
+ {{- "<｜User｜>" + message["content"] -}}
16
+ {%- endif -%}
17
+
18
+ {%- if message["role"] == "assistant" and message["content"] is none -%}
19
+ {%- set ns.is_tool = false -%}
20
+ {%- for tool in message["tool_calls"] -%}
21
+ {%- if not ns.is_first -%}
22
+ {{- "<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>" + tool["type"] + "<｜tool▁sep｜>" + tool["function"]["name"] + "\n" + "```json" + "\n" + tool["function"]["arguments"] + "\n" + "```" + "<｜tool▁call▁end｜>" -}}
23
+ {%- set ns.is_first = true -%}
24
+ {%- else -%}
25
+ {{- "\n" + "<｜tool▁call▁begin｜>" + tool["type"] + "<｜tool▁sep｜>" + tool["function"]["name"] + "\n" + "```json" + "\n" + tool["function"]["arguments"] + "\n" + "```" + "<｜tool▁call▁end｜>" -}}
26
+ {{- "<｜tool▁calls▁end｜><｜end▁of▁sentence｜>" -}}
27
+ {%- endif -%}
28
+ {%- endfor -%}
29
+ {%- endif -%}
30
+
31
+ {%- if message["role"] == "assistant" and message["content"] is not none -%}
32
+ {%- if ns.is_tool -%}
33
+ {{- "<｜tool▁outputs▁end｜>" + message["content"] + "<｜end▁of▁sentence｜>" -}}
34
+ {%- set ns.is_tool = false -%}
35
+ {%- else -%}
36
+ {%- set content = message["content"] -%}
37
+ {%- if "</think>" in content -%}
38
+ {%- set content = content.split("</think>")[-1] -%}
39
+ {%- endif -%}
40
+ {% generation %}
41
+ {{- "<｜Assistant｜>" + content + "<｜end▁of▁sentence｜>" -}}
42
+ {% endgeneration %}
43
+ {%- endif -%}
44
+ {%- endif -%}
45
+
46
+ {%- if message["role"] == "tool" -%}
47
+ {%- set ns.is_tool = true -%}
48
+ {%- if ns.is_output_first -%}
49
+ {{- "<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>" + message["content"] + "<｜tool▁output▁end｜>" -}}
50
+ {%- set ns.is_output_first = false -%}
51
+ {%- else -%}
52
+ {{- "\n<｜tool▁output▁begin｜>" + message["content"] + "<｜tool▁output▁end｜>" -}}
53
+ {%- endif -%}
54
+ {%- endif -%}
55
+ {%- endfor -%}
56
+
57
+ {%- if ns.is_tool -%}
58
+ {{- "<｜tool▁outputs▁end｜>" -}}
59
+ {%- endif -%}
60
+
61
+ {%- if add_generation_prompt and not ns.is_tool -%}
62
+ {% generation %}
63
+ {{- "<｜Assistant｜><think>\n" -}}
64
+ {% endgeneration %}
65
+ {%- endif -%}
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AutoDecoModelForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
7
+ "base_model_type": "qwen2",
8
+ "bos_token_id": 151643,
9
+ "dtype": "bfloat16",
10
+ "enable_temperature_head": true,
11
+ "enable_top_p_head": true,
12
+ "eos_token_id": 151643,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "layer_types": [
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
+ ],
47
+ "max_position_embeddings": 131072,
48
+ "max_window_layers": 28,
49
+ "model_type": "autodeco",
50
+ "num_attention_heads": 28,
51
+ "num_hidden_layers": 28,
52
+ "num_key_value_heads": 4,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_scaling": null,
55
+ "rope_theta": 10000,
56
+ "sliding_window": null,
57
+ "temperature_hidden_size": 3584,
58
+ "tie_word_embeddings": false,
59
+ "top_p_hidden_size": 3584,
60
+ "transformers_version": "4.57.1",
61
+ "use_cache": true,
62
+ "use_enhanced_features": true,
63
+ "use_mrope": false,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 152064
66
+ }
chat_template.jinja ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if not add_generation_prompt is defined -%}
2
+ {%- set add_generation_prompt = false -%}
3
+ {%- endif -%}
4
+ {%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt="") -%}
5
+ {%- for message in messages -%}
6
+ {%- if message["role"] == "system" -%}
7
+ {%- set ns.system_prompt = message["content"] -%}
8
+ {%- endif -%}
9
+ {%- endfor -%}
10
+ {{- bos_token -}}
11
+ {{- ns.system_prompt -}}
12
+ {%- for message in messages -%}
13
+ {%- if message["role"] == "user" -%}
14
+ {%- set ns.is_tool = false -%}
15
+ {{- "<｜User｜>" + message["content"] -}}
16
+ {%- endif -%}
17
+
18
+ {%- if message["role"] == "assistant" and message["content"] is none -%}
19
+ {%- set ns.is_tool = false -%}
20
+ {%- for tool in message["tool_calls"] -%}
21
+ {%- if not ns.is_first -%}
22
+ {{- "<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>" + tool["type"] + "<｜tool▁sep｜>" + tool["function"]["name"] + "\n" + "```json" + "\n" + tool["function"]["arguments"] + "\n" + "```" + "<｜tool▁call▁end｜>" -}}
23
+ {%- set ns.is_first = true -%}
24
+ {%- else -%}
25
+ {{- "\n" + "<｜tool▁call▁begin｜>" + tool["type"] + "<｜tool▁sep｜>" + tool["function"]["name"] + "\n" + "```json" + "\n" + tool["function"]["arguments"] + "\n" + "```" + "<｜tool▁call▁end｜>" -}}
26
+ {{- "<｜tool▁calls▁end｜><｜end▁of▁sentence｜>" -}}
27
+ {%- endif -%}
28
+ {%- endfor -%}
29
+ {%- endif -%}
30
+
31
+ {%- if message["role"] == "assistant" and message["content"] is not none -%}
32
+ {%- if ns.is_tool -%}
33
+ {{- "<｜tool▁outputs▁end｜>" + message["content"] + "<｜end▁of▁sentence｜>" -}}
34
+ {%- set ns.is_tool = false -%}
35
+ {%- else -%}
36
+ {%- set content = message["content"] -%}
37
+ {%- if "</think>" in content -%}
38
+ {%- set content = content.split("</think>")[-1] -%}
39
+ {%- endif -%}
40
+ {% generation %}
41
+ {{- "<｜Assistant｜>" + content + "<｜end▁of▁sentence｜>" -}}
42
+ {% endgeneration %}
43
+ {%- endif -%}
44
+ {%- endif -%}
45
+
46
+ {%- if message["role"] == "tool" -%}
47
+ {%- set ns.is_tool = true -%}
48
+ {%- if ns.is_output_first -%}
49
+ {{- "<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>" + message["content"] + "<｜tool▁output▁end｜>" -}}
50
+ {%- set ns.is_output_first = false -%}
51
+ {%- else -%}
52
+ {{- "\n<｜tool▁output▁begin｜>" + message["content"] + "<｜tool▁output▁end｜>" -}}
53
+ {%- endif -%}
54
+ {%- endif -%}
55
+ {%- endfor -%}
56
+
57
+ {%- if ns.is_tool -%}
58
+ {{- "<｜tool▁outputs▁end｜>" -}}
59
+ {%- endif -%}
60
+
61
+ {%- if add_generation_prompt and not ns.is_tool -%}
62
+ {% generation %}
63
+ {{- "<｜Assistant｜><think>\n" -}}
64
+ {% endgeneration %}
65
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AutoDecoModelForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
7
+ "base_model_type": "qwen2",
8
+ "bos_token_id": 151643,
9
+ "dtype": "bfloat16",
10
+ "enable_temperature_head": true,
11
+ "enable_top_p_head": true,
12
+ "eos_token_id": 151643,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "layer_types": [
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
+ ],
47
+ "max_position_embeddings": 131072,
48
+ "max_window_layers": 28,
49
+ "model_type": "autodeco",
50
+ "num_attention_heads": 28,
51
+ "num_hidden_layers": 28,
52
+ "num_key_value_heads": 4,
53
+ "rms_norm_eps": 1e-06,
54
+ "rope_scaling": null,
55
+ "rope_theta": 10000,
56
+ "sliding_window": null,
57
+ "temperature_hidden_size": 3584,
58
+ "tie_word_embeddings": false,
59
+ "top_p_hidden_size": 3584,
60
+ "transformers_version": "4.57.1",
61
+ "use_cache": true,
62
+ "use_enhanced_features": true,
63
+ "use_mrope": false,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 152064
66
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "eos_token_id": 151643,
5
+ "do_sample": true,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.39.3"
9
+ }
model-00001-of-000002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2eb043ded0a2e1fa457017ea0aeb7fa402a6a3d6f759cb6142e61558290396
3
+ size 8606597240
model-00002-of-000002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e3f3bd622afbb65db4c1095d4a2b3c715ef0c109c32967bc78c0674ba7885d
3
+ size 6628351356
model.safetensors.index.json ADDED
@@ -0,0 +1,354 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15231233024
4
+ },
5
+ "weight_map": {
6
+ "llm.model.embed_tokens.weight": "model-00001-of-000002.safetensors",
7
+ "llm.model.layers.0.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
8
+ "llm.model.layers.0.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
9
+ "llm.model.layers.0.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
10
+ "llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
11
+ "llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
12
+ "llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
13
+ "llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
14
+ "llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
15
+ "llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
16
+ "llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
17
+ "llm.model.layers.0.input_layernorm.weight": "model-00001-of-000002.safetensors",
18
+ "llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
19
+ "llm.model.layers.1.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
20
+ "llm.model.layers.1.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
21
+ "llm.model.layers.1.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
22
+ "llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
23
+ "llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
24
+ "llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
25
+ "llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
26
+ "llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
27
+ "llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
28
+ "llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
29
+ "llm.model.layers.1.input_layernorm.weight": "model-00001-of-000002.safetensors",
30
+ "llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
31
+ "llm.model.layers.2.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
32
+ "llm.model.layers.2.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
33
+ "llm.model.layers.2.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
34
+ "llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
35
+ "llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
36
+ "llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
37
+ "llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
38
+ "llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
39
+ "llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
40
+ "llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
41
+ "llm.model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors",
42
+ "llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
43
+ "llm.model.layers.3.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
44
+ "llm.model.layers.3.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
45
+ "llm.model.layers.3.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
46
+ "llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
47
+ "llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
48
+ "llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
49
+ "llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
50
+ "llm.model.layers.3.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
51
+ "llm.model.layers.3.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
52
+ "llm.model.layers.3.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
53
+ "llm.model.layers.3.input_layernorm.weight": "model-00001-of-000002.safetensors",
54
+ "llm.model.layers.3.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
55
+ "llm.model.layers.4.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
56
+ "llm.model.layers.4.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
57
+ "llm.model.layers.4.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
58
+ "llm.model.layers.4.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
59
+ "llm.model.layers.4.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
60
+ "llm.model.layers.4.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
61
+ "llm.model.layers.4.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
62
+ "llm.model.layers.4.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
63
+ "llm.model.layers.4.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
64
+ "llm.model.layers.4.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
65
+ "llm.model.layers.4.input_layernorm.weight": "model-00001-of-000002.safetensors",
66
+ "llm.model.layers.4.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
67
+ "llm.model.layers.5.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
68
+ "llm.model.layers.5.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
69
+ "llm.model.layers.5.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
70
+ "llm.model.layers.5.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
71
+ "llm.model.layers.5.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
72
+ "llm.model.layers.5.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
73
+ "llm.model.layers.5.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
74
+ "llm.model.layers.5.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
75
+ "llm.model.layers.5.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
76
+ "llm.model.layers.5.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
77
+ "llm.model.layers.5.input_layernorm.weight": "model-00001-of-000002.safetensors",
78
+ "llm.model.layers.5.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
79
+ "llm.model.layers.6.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
80
+ "llm.model.layers.6.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
81
+ "llm.model.layers.6.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
82
+ "llm.model.layers.6.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
83
+ "llm.model.layers.6.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
84
+ "llm.model.layers.6.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
85
+ "llm.model.layers.6.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
86
+ "llm.model.layers.6.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
87
+ "llm.model.layers.6.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
88
+ "llm.model.layers.6.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
89
+ "llm.model.layers.6.input_layernorm.weight": "model-00001-of-000002.safetensors",
90
+ "llm.model.layers.6.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
91
+ "llm.model.layers.7.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
92
+ "llm.model.layers.7.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
93
+ "llm.model.layers.7.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
94
+ "llm.model.layers.7.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
95
+ "llm.model.layers.7.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
96
+ "llm.model.layers.7.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
97
+ "llm.model.layers.7.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
98
+ "llm.model.layers.7.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
99
+ "llm.model.layers.7.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
100
+ "llm.model.layers.7.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
101
+ "llm.model.layers.7.input_layernorm.weight": "model-00001-of-000002.safetensors",
102
+ "llm.model.layers.7.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
103
+ "llm.model.layers.8.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
104
+ "llm.model.layers.8.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
105
+ "llm.model.layers.8.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
106
+ "llm.model.layers.8.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
107
+ "llm.model.layers.8.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
108
+ "llm.model.layers.8.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
109
+ "llm.model.layers.8.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
110
+ "llm.model.layers.8.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
111
+ "llm.model.layers.8.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
112
+ "llm.model.layers.8.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
113
+ "llm.model.layers.8.input_layernorm.weight": "model-00001-of-000002.safetensors",
114
+ "llm.model.layers.8.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
115
+ "llm.model.layers.9.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
116
+ "llm.model.layers.9.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
117
+ "llm.model.layers.9.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
118
+ "llm.model.layers.9.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
119
+ "llm.model.layers.9.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
120
+ "llm.model.layers.9.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
121
+ "llm.model.layers.9.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
122
+ "llm.model.layers.9.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
123
+ "llm.model.layers.9.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
124
+ "llm.model.layers.9.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
125
+ "llm.model.layers.9.input_layernorm.weight": "model-00001-of-000002.safetensors",
126
+ "llm.model.layers.9.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
127
+ "llm.model.layers.10.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
128
+ "llm.model.layers.10.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
129
+ "llm.model.layers.10.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
130
+ "llm.model.layers.10.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
131
+ "llm.model.layers.10.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
132
+ "llm.model.layers.10.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
133
+ "llm.model.layers.10.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
134
+ "llm.model.layers.10.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
135
+ "llm.model.layers.10.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
136
+ "llm.model.layers.10.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
137
+ "llm.model.layers.10.input_layernorm.weight": "model-00001-of-000002.safetensors",
138
+ "llm.model.layers.10.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
139
+ "llm.model.layers.11.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
140
+ "llm.model.layers.11.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
141
+ "llm.model.layers.11.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
142
+ "llm.model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
143
+ "llm.model.layers.11.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
144
+ "llm.model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
145
+ "llm.model.layers.11.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
146
+ "llm.model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
147
+ "llm.model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
148
+ "llm.model.layers.11.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
149
+ "llm.model.layers.11.input_layernorm.weight": "model-00001-of-000002.safetensors",
150
+ "llm.model.layers.11.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
151
+ "llm.model.layers.12.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
152
+ "llm.model.layers.12.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
153
+ "llm.model.layers.12.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
154
+ "llm.model.layers.12.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
155
+ "llm.model.layers.12.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
156
+ "llm.model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
157
+ "llm.model.layers.12.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
158
+ "llm.model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
159
+ "llm.model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
160
+ "llm.model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
161
+ "llm.model.layers.12.input_layernorm.weight": "model-00001-of-000002.safetensors",
162
+ "llm.model.layers.12.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
163
+ "llm.model.layers.13.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
164
+ "llm.model.layers.13.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
165
+ "llm.model.layers.13.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
166
+ "llm.model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
167
+ "llm.model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
168
+ "llm.model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
169
+ "llm.model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
170
+ "llm.model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
171
+ "llm.model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
172
+ "llm.model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
173
+ "llm.model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors",
174
+ "llm.model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
175
+ "llm.model.layers.14.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
176
+ "llm.model.layers.14.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
177
+ "llm.model.layers.14.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
178
+ "llm.model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
179
+ "llm.model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
180
+ "llm.model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
181
+ "llm.model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
182
+ "llm.model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
183
+ "llm.model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
184
+ "llm.model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
185
+ "llm.model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors",
186
+ "llm.model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
187
+ "llm.model.layers.15.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
188
+ "llm.model.layers.15.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
189
+ "llm.model.layers.15.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
190
+ "llm.model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
191
+ "llm.model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
192
+ "llm.model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
193
+ "llm.model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
194
+ "llm.model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
195
+ "llm.model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
196
+ "llm.model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
197
+ "llm.model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors",
198
+ "llm.model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
199
+ "llm.model.layers.16.self_attn.q_proj.bias": "model-00001-of-000002.safetensors",
200
+ "llm.model.layers.16.self_attn.k_proj.bias": "model-00001-of-000002.safetensors",
201
+ "llm.model.layers.16.self_attn.v_proj.bias": "model-00001-of-000002.safetensors",
202
+ "llm.model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
203
+ "llm.model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
204
+ "llm.model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
205
+ "llm.model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
206
+ "llm.model.layers.16.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
207
+ "llm.model.layers.16.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
208
+ "llm.model.layers.16.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
209
+ "llm.model.layers.16.input_layernorm.weight": "model-00002-of-000002.safetensors",
210
+ "llm.model.layers.16.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
211
+ "llm.model.layers.17.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
212
+ "llm.model.layers.17.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
213
+ "llm.model.layers.17.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
214
+ "llm.model.layers.17.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
215
+ "llm.model.layers.17.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
216
+ "llm.model.layers.17.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
217
+ "llm.model.layers.17.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
218
+ "llm.model.layers.17.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
219
+ "llm.model.layers.17.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
220
+ "llm.model.layers.17.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
221
+ "llm.model.layers.17.input_layernorm.weight": "model-00002-of-000002.safetensors",
222
+ "llm.model.layers.17.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
223
+ "llm.model.layers.18.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
224
+ "llm.model.layers.18.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
225
+ "llm.model.layers.18.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
226
+ "llm.model.layers.18.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
227
+ "llm.model.layers.18.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
228
+ "llm.model.layers.18.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
229
+ "llm.model.layers.18.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
230
+ "llm.model.layers.18.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
231
+ "llm.model.layers.18.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
232
+ "llm.model.layers.18.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
233
+ "llm.model.layers.18.input_layernorm.weight": "model-00002-of-000002.safetensors",
234
+ "llm.model.layers.18.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
235
+ "llm.model.layers.19.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
236
+ "llm.model.layers.19.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
237
+ "llm.model.layers.19.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
238
+ "llm.model.layers.19.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
239
+ "llm.model.layers.19.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
240
+ "llm.model.layers.19.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
241
+ "llm.model.layers.19.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
242
+ "llm.model.layers.19.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
243
+ "llm.model.layers.19.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
244
+ "llm.model.layers.19.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
245
+ "llm.model.layers.19.input_layernorm.weight": "model-00002-of-000002.safetensors",
246
+ "llm.model.layers.19.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
247
+ "llm.model.layers.20.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
248
+ "llm.model.layers.20.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
249
+ "llm.model.layers.20.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
250
+ "llm.model.layers.20.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
251
+ "llm.model.layers.20.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
252
+ "llm.model.layers.20.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
253
+ "llm.model.layers.20.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
254
+ "llm.model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
255
+ "llm.model.layers.20.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
256
+ "llm.model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
257
+ "llm.model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors",
258
+ "llm.model.layers.20.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
259
+ "llm.model.layers.21.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
260
+ "llm.model.layers.21.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
261
+ "llm.model.layers.21.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
262
+ "llm.model.layers.21.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
263
+ "llm.model.layers.21.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
264
+ "llm.model.layers.21.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
265
+ "llm.model.layers.21.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
266
+ "llm.model.layers.21.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
267
+ "llm.model.layers.21.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
268
+ "llm.model.layers.21.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
269
+ "llm.model.layers.21.input_layernorm.weight": "model-00002-of-000002.safetensors",
270
+ "llm.model.layers.21.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
271
+ "llm.model.layers.22.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
272
+ "llm.model.layers.22.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
273
+ "llm.model.layers.22.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
274
+ "llm.model.layers.22.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
275
+ "llm.model.layers.22.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
276
+ "llm.model.layers.22.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
277
+ "llm.model.layers.22.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
278
+ "llm.model.layers.22.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
279
+ "llm.model.layers.22.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
280
+ "llm.model.layers.22.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
281
+ "llm.model.layers.22.input_layernorm.weight": "model-00002-of-000002.safetensors",
282
+ "llm.model.layers.22.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
283
+ "llm.model.layers.23.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
284
+ "llm.model.layers.23.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
285
+ "llm.model.layers.23.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
286
+ "llm.model.layers.23.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
287
+ "llm.model.layers.23.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
288
+ "llm.model.layers.23.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
289
+ "llm.model.layers.23.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
290
+ "llm.model.layers.23.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
291
+ "llm.model.layers.23.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
292
+ "llm.model.layers.23.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
293
+ "llm.model.layers.23.input_layernorm.weight": "model-00002-of-000002.safetensors",
294
+ "llm.model.layers.23.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
295
+ "llm.model.layers.24.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
296
+ "llm.model.layers.24.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
297
+ "llm.model.layers.24.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
298
+ "llm.model.layers.24.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
299
+ "llm.model.layers.24.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
300
+ "llm.model.layers.24.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
301
+ "llm.model.layers.24.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
302
+ "llm.model.layers.24.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
303
+ "llm.model.layers.24.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
304
+ "llm.model.layers.24.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
305
+ "llm.model.layers.24.input_layernorm.weight": "model-00002-of-000002.safetensors",
306
+ "llm.model.layers.24.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
307
+ "llm.model.layers.25.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
308
+ "llm.model.layers.25.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
309
+ "llm.model.layers.25.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
310
+ "llm.model.layers.25.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
311
+ "llm.model.layers.25.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
312
+ "llm.model.layers.25.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
313
+ "llm.model.layers.25.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
314
+ "llm.model.layers.25.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
315
+ "llm.model.layers.25.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
316
+ "llm.model.layers.25.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
317
+ "llm.model.layers.25.input_layernorm.weight": "model-00002-of-000002.safetensors",
318
+ "llm.model.layers.25.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
319
+ "llm.model.layers.26.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
320
+ "llm.model.layers.26.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
321
+ "llm.model.layers.26.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
322
+ "llm.model.layers.26.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
323
+ "llm.model.layers.26.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
324
+ "llm.model.layers.26.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
325
+ "llm.model.layers.26.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
326
+ "llm.model.layers.26.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
327
+ "llm.model.layers.26.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
328
+ "llm.model.layers.26.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
329
+ "llm.model.layers.26.input_layernorm.weight": "model-00002-of-000002.safetensors",
330
+ "llm.model.layers.26.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
331
+ "llm.model.layers.27.self_attn.q_proj.bias": "model-00002-of-000002.safetensors",
332
+ "llm.model.layers.27.self_attn.k_proj.bias": "model-00002-of-000002.safetensors",
333
+ "llm.model.layers.27.self_attn.v_proj.bias": "model-00002-of-000002.safetensors",
334
+ "llm.model.layers.27.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
335
+ "llm.model.layers.27.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
336
+ "llm.model.layers.27.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
337
+ "llm.model.layers.27.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
338
+ "llm.model.layers.27.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
339
+ "llm.model.layers.27.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
340
+ "llm.model.layers.27.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
341
+ "llm.model.layers.27.input_layernorm.weight": "model-00002-of-000002.safetensors",
342
+ "llm.model.layers.27.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
343
+ "llm.model.norm.weight": "model-00002-of-000002.safetensors",
344
+ "llm.lm_head.weight": "model-00002-of-000002.safetensors",
345
+ "temp_head.mlp.0.bias": "model-00002-of-000002.safetensors",
346
+ "temp_head.mlp.0.weight": "model-00002-of-000002.safetensors",
347
+ "temp_head.mlp.2.bias": "model-00002-of-000002.safetensors",
348
+ "temp_head.mlp.2.weight": "model-00002-of-000002.safetensors",
349
+ "top_p_head.mlp.0.bias": "model-00002-of-000002.safetensors",
350
+ "top_p_head.mlp.0.weight": "model-00002-of-000002.safetensors",
351
+ "top_p_head.mlp.2.bias": "model-00002-of-000002.safetensors",
352
+ "top_p_head.mlp.2.weight": "model-00002-of-000002.safetensors"
353
+ }
354
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<｜begin▁of▁sentence｜>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 16384,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<｜end▁of▁sentence｜>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "LlamaTokenizerFast",
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
35
+ }