Hugging Face's logo

Columbidae
/
qwen-depth-upscaled-60

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
 Community
ToastyPigeon commited on
Commit
35a7ff5
·
verified ·
1 Parent(s): 0f939cb

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/config-checkpoint.json +33 -0
  3. README.md +193 -0
  4. added_tokens.json +24 -0
  5. config.json +33 -0
  6. mergekit_config.yml +164 -0
  7. merges.txt +0 -0
  8. model-00001-of-00008.safetensors +3 -0
  9. model-00002-of-00008.safetensors +3 -0
  10. model-00003-of-00008.safetensors +3 -0
  11. model-00004-of-00008.safetensors +3 -0
  12. model-00005-of-00008.safetensors +3 -0
  13. model-00006-of-00008.safetensors +3 -0
  14. model-00007-of-00008.safetensors +3 -0
  15. model-00008-of-00008.safetensors +3 -0
  16. model.safetensors.index.json +1 -0
  17. special_tokens_map.json +31 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +208 -0
  20. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ToastyPigeon/qwen2.5-14b-1m-unalign-v2",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dual_chunk_attention_config": {
8
+ "chunk_size": 262144,
9
+ "local_size": 8192,
10
+ "original_max_position_embeddings": 262144
11
+ },
12
+ "eos_token_id": 151645,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13824,
17
+ "max_position_embeddings": 1010000,
18
+ "max_window_layers": 48,
19
+ "model_type": "qwen2",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 60,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000000.0,
26
+ "sliding_window": 1010000,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.49.0",
30
+ "use_cache": false,
31
+ "use_sliding_window": false,
32
+ "vocab_size": 152064
33
+ }
README.md ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - ToastyPigeon/qwen2.5-14b-1m-unalign-v2
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # qwen60l
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the Passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [ToastyPigeon/qwen2.5-14b-1m-unalign-v2](https://huggingface.co/ToastyPigeon/qwen2.5-14b-1m-unalign-v2)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
32
+ layer_range: [0,30]
33
+ - sources:
34
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
35
+ layer_range: [30,31]
36
+ - sources:
37
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
38
+ layer_range: [30,31]
39
+ parameters:
40
+ scale:
41
+ - filter: o_proj
42
+ value: 0.0
43
+ - filter: down_proj
44
+ value: 0.0
45
+ - value: 1.0
46
+ - sources:
47
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
48
+ layer_range: [31,32]
49
+ - sources:
50
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
51
+ layer_range: [31,32]
52
+ parameters:
53
+ scale:
54
+ - filter: o_proj
55
+ value: 0.0
56
+ - filter: down_proj
57
+ value: 0.0
58
+ - value: 1.0
59
+ - sources:
60
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
61
+ layer_range: [32,33]
62
+ - sources:
63
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
64
+ layer_range: [32,33]
65
+ parameters:
66
+ scale:
67
+ - filter: o_proj
68
+ value: 0.0
69
+ - filter: down_proj
70
+ value: 0.0
71
+ - value: 1.0
72
+ - sources:
73
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
74
+ layer_range: [33,34]
75
+ - sources:
76
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
77
+ layer_range: [33,34]
78
+ parameters:
79
+ scale:
80
+ - filter: o_proj
81
+ value: 0.0
82
+ - filter: down_proj
83
+ value: 0.0
84
+ - value: 1.0
85
+ - sources:
86
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
87
+ layer_range: [34,35]
88
+ - sources:
89
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
90
+ layer_range: [34,35]
91
+ parameters:
92
+ scale:
93
+ - filter: o_proj
94
+ value: 0.0
95
+ - filter: down_proj
96
+ value: 0.0
97
+ - value: 1.0
98
+ - sources:
99
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
100
+ layer_range: [35,36]
101
+ - sources:
102
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
103
+ layer_range: [35,36]
104
+ parameters:
105
+ scale:
106
+ - filter: o_proj
107
+ value: 0.0
108
+ - filter: down_proj
109
+ value: 0.0
110
+ - value: 1.0
111
+ - sources:
112
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
113
+ layer_range: [36,37]
114
+ - sources:
115
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
116
+ layer_range: [36,37]
117
+ parameters:
118
+ scale:
119
+ - filter: o_proj
120
+ value: 0.0
121
+ - filter: down_proj
122
+ value: 0.0
123
+ - value: 1.0
124
+ - sources:
125
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
126
+ layer_range: [37,38]
127
+ - sources:
128
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
129
+ layer_range: [37,38]
130
+ parameters:
131
+ scale:
132
+ - filter: o_proj
133
+ value: 0.0
134
+ - filter: down_proj
135
+ value: 0.0
136
+ - value: 1.0
137
+ - sources:
138
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
139
+ layer_range: [38,39]
140
+ - sources:
141
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
142
+ layer_range: [38,39]
143
+ parameters:
144
+ scale:
145
+ - filter: o_proj
146
+ value: 0.0
147
+ - filter: down_proj
148
+ value: 0.0
149
+ - value: 1.0
150
+ - sources:
151
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
152
+ layer_range: [39,40]
153
+ - sources:
154
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
155
+ layer_range: [39,40]
156
+ parameters:
157
+ scale:
158
+ - filter: o_proj
159
+ value: 0.0
160
+ - filter: down_proj
161
+ value: 0.0
162
+ - value: 1.0
163
+ - sources:
164
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
165
+ layer_range: [40,41]
166
+ - sources:
167
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
168
+ layer_range: [40,41]
169
+ parameters:
170
+ scale:
171
+ - filter: o_proj
172
+ value: 0.0
173
+ - filter: down_proj
174
+ value: 0.0
175
+ - value: 1.0
176
+ - sources:
177
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
178
+ layer_range: [41,42]
179
+ - sources:
180
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
181
+ layer_range: [41,42]
182
+ parameters:
183
+ scale:
184
+ - filter: o_proj
185
+ value: 0.0
186
+ - filter: down_proj
187
+ value: 0.0
188
+ - value: 1.0
189
+ - sources:
190
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
191
+ layer_range: [42,48]
192
+ merge_method: passthrough
193
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ToastyPigeon/qwen2.5-14b-1m-unalign-v2",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dual_chunk_attention_config": {
8
+ "chunk_size": 262144,
9
+ "local_size": 8192,
10
+ "original_max_position_embeddings": 262144
11
+ },
12
+ "eos_token_id": 151645,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 5120,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 13824,
17
+ "max_position_embeddings": 1010000,
18
+ "max_window_layers": 48,
19
+ "model_type": "qwen2",
20
+ "num_attention_heads": 40,
21
+ "num_hidden_layers": 60,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000000.0,
26
+ "sliding_window": 1010000,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.49.0",
30
+ "use_cache": false,
31
+ "use_sliding_window": false,
32
+ "vocab_size": 152064
33
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
4
+ layer_range: [0,30]
5
+ - sources:
6
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
7
+ layer_range: [30,31]
8
+ - sources:
9
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
10
+ layer_range: [30,31]
11
+ parameters:
12
+ scale:
13
+ - filter: o_proj
14
+ value: 0.0
15
+ - filter: down_proj
16
+ value: 0.0
17
+ - value: 1.0
18
+ - sources:
19
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
20
+ layer_range: [31,32]
21
+ - sources:
22
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
23
+ layer_range: [31,32]
24
+ parameters:
25
+ scale:
26
+ - filter: o_proj
27
+ value: 0.0
28
+ - filter: down_proj
29
+ value: 0.0
30
+ - value: 1.0
31
+ - sources:
32
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
33
+ layer_range: [32,33]
34
+ - sources:
35
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
36
+ layer_range: [32,33]
37
+ parameters:
38
+ scale:
39
+ - filter: o_proj
40
+ value: 0.0
41
+ - filter: down_proj
42
+ value: 0.0
43
+ - value: 1.0
44
+ - sources:
45
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
46
+ layer_range: [33,34]
47
+ - sources:
48
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
49
+ layer_range: [33,34]
50
+ parameters:
51
+ scale:
52
+ - filter: o_proj
53
+ value: 0.0
54
+ - filter: down_proj
55
+ value: 0.0
56
+ - value: 1.0
57
+ - sources:
58
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
59
+ layer_range: [34,35]
60
+ - sources:
61
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
62
+ layer_range: [34,35]
63
+ parameters:
64
+ scale:
65
+ - filter: o_proj
66
+ value: 0.0
67
+ - filter: down_proj
68
+ value: 0.0
69
+ - value: 1.0
70
+ - sources:
71
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
72
+ layer_range: [35,36]
73
+ - sources:
74
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
75
+ layer_range: [35,36]
76
+ parameters:
77
+ scale:
78
+ - filter: o_proj
79
+ value: 0.0
80
+ - filter: down_proj
81
+ value: 0.0
82
+ - value: 1.0
83
+ - sources:
84
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
85
+ layer_range: [36,37]
86
+ - sources:
87
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
88
+ layer_range: [36,37]
89
+ parameters:
90
+ scale:
91
+ - filter: o_proj
92
+ value: 0.0
93
+ - filter: down_proj
94
+ value: 0.0
95
+ - value: 1.0
96
+ - sources:
97
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
98
+ layer_range: [37,38]
99
+ - sources:
100
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
101
+ layer_range: [37,38]
102
+ parameters:
103
+ scale:
104
+ - filter: o_proj
105
+ value: 0.0
106
+ - filter: down_proj
107
+ value: 0.0
108
+ - value: 1.0
109
+ - sources:
110
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
111
+ layer_range: [38,39]
112
+ - sources:
113
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
114
+ layer_range: [38,39]
115
+ parameters:
116
+ scale:
117
+ - filter: o_proj
118
+ value: 0.0
119
+ - filter: down_proj
120
+ value: 0.0
121
+ - value: 1.0
122
+ - sources:
123
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
124
+ layer_range: [39,40]
125
+ - sources:
126
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
127
+ layer_range: [39,40]
128
+ parameters:
129
+ scale:
130
+ - filter: o_proj
131
+ value: 0.0
132
+ - filter: down_proj
133
+ value: 0.0
134
+ - value: 1.0
135
+ - sources:
136
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
137
+ layer_range: [40,41]
138
+ - sources:
139
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
140
+ layer_range: [40,41]
141
+ parameters:
142
+ scale:
143
+ - filter: o_proj
144
+ value: 0.0
145
+ - filter: down_proj
146
+ value: 0.0
147
+ - value: 1.0
148
+ - sources:
149
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
150
+ layer_range: [41,42]
151
+ - sources:
152
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
153
+ layer_range: [41,42]
154
+ parameters:
155
+ scale:
156
+ - filter: o_proj
157
+ value: 0.0
158
+ - filter: down_proj
159
+ value: 0.0
160
+ - value: 1.0
161
+ - sources:
162
+ - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
163
+ layer_range: [42,48]
164
+ merge_method: passthrough
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57664c11a8ca406bbe199044428614b15c2bd9b025016fcd02a7c9c23b57fd6b
3
+ size 4907454960
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afada7fd03813433f090df60c7317a685655d69ee0b65cdf9ad7a280961a227
3
+ size 4954847384
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6424cf64f029dc0b0a6afc4e28bed7a7962bbc5c72908e691b61dada9f7bd40
3
+ size 4954847376
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5217f9bf7685937c8b03752807e5379eb85760f1bd1b5073803de6e303e8213
3
+ size 4954857728
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889e9620fefcd86f269f15e2490344226f14f9aafabd919234f4cfcbae2c73af
3
+ size 4970540296
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9c27591caf1da2e886456524d59d8d1f2ae89f7a232a08d2e5ebb85732cbe7
3
+ size 4954847352
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e482eedb444180adebd4b46d70fc4219112adf43a48ed59b7a9e63b10a3474
3
+ size 4939144088
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ef6d7166df2836ba87b09f41cc7919d4bcf71ee5fa7a88b259269826be9672
3
+ size 1510057856
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.6", "total_size": 36146513920}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00004-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00006-of-00008.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00007-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 1010000,
204
+ "pad_token": "<|endoftext|>",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff