ClaudioItaly
commited on
Commit
•
464c472
1
Parent(s):
61a49da
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +51 -0
- added_tokens.json +24 -0
- config.json +29 -0
- mergekit_config.yml +21 -0
- merges.txt +0 -0
- model-00001-of-00030.safetensors +3 -0
- model-00002-of-00030.safetensors +3 -0
- model-00003-of-00030.safetensors +3 -0
- model-00004-of-00030.safetensors +3 -0
- model-00005-of-00030.safetensors +3 -0
- model-00006-of-00030.safetensors +3 -0
- model-00007-of-00030.safetensors +3 -0
- model-00008-of-00030.safetensors +3 -0
- model-00009-of-00030.safetensors +3 -0
- model-00010-of-00030.safetensors +3 -0
- model-00011-of-00030.safetensors +3 -0
- model-00012-of-00030.safetensors +3 -0
- model-00013-of-00030.safetensors +3 -0
- model-00014-of-00030.safetensors +3 -0
- model-00015-of-00030.safetensors +3 -0
- model-00016-of-00030.safetensors +3 -0
- model-00017-of-00030.safetensors +3 -0
- model-00018-of-00030.safetensors +3 -0
- model-00019-of-00030.safetensors +3 -0
- model-00020-of-00030.safetensors +3 -0
- model-00021-of-00030.safetensors +3 -0
- model-00022-of-00030.safetensors +3 -0
- model-00023-of-00030.safetensors +3 -0
- model-00024-of-00030.safetensors +3 -0
- model-00025-of-00030.safetensors +3 -0
- model-00026-of-00030.safetensors +3 -0
- model-00027-of-00030.safetensors +3 -0
- model-00028-of-00030.safetensors +3 -0
- model-00029-of-00030.safetensors +3 -0
- model-00030-of-00030.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +207 -0
- 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
|
README.md
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-Coder-7B-Instruct
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
|
9 |
+
---
|
10 |
+
# merge
|
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 SLERP merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
models:
|
30 |
+
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
31 |
+
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
32 |
+
merge_method: slerp
|
33 |
+
tokenizer_merge_method: slerp
|
34 |
+
tokenizer_parameters:
|
35 |
+
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
36 |
+
dtype: bfloat16
|
37 |
+
parameters:
|
38 |
+
t: [0, 0.3, 0.6, 0.8, 0.6, 0.3, 0] # Curva che favorisce leggermente il centro del merge
|
39 |
+
temp: 1.0 # Temperatura aumentata per un merge più audace
|
40 |
+
density:
|
41 |
+
- threshold: 0.05
|
42 |
+
t: 0.8
|
43 |
+
- threshold: 0.3
|
44 |
+
t: 0.6
|
45 |
+
- threshold: 0.7
|
46 |
+
t: 0.4
|
47 |
+
- threshold: 0.95
|
48 |
+
t: 0.2
|
49 |
+
noise: 0.1 # Aggiunto rumore per ulteriore variabilità
|
50 |
+
|
51 |
+
```
|
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 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3584,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 18944,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 28,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 28,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 4,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 1000000.0,
|
22 |
+
"sliding_window": null,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.45.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"use_sliding_window": false,
|
28 |
+
"vocab_size": 152064
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
3 |
+
- model: Qwen/Qwen2.5-Coder-7B-Instruct
|
4 |
+
merge_method: slerp
|
5 |
+
tokenizer_merge_method: slerp
|
6 |
+
tokenizer_parameters:
|
7 |
+
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
8 |
+
dtype: bfloat16
|
9 |
+
parameters:
|
10 |
+
t: [0, 0.3, 0.6, 0.8, 0.6, 0.3, 0] # Curva che favorisce leggermente il centro del merge
|
11 |
+
temp: 1.0 # Temperatura aumentata per un merge più audace
|
12 |
+
density:
|
13 |
+
- threshold: 0.05
|
14 |
+
t: 0.8
|
15 |
+
- threshold: 0.3
|
16 |
+
t: 0.6
|
17 |
+
- threshold: 0.7
|
18 |
+
t: 0.4
|
19 |
+
- threshold: 0.95
|
20 |
+
t: 0.2
|
21 |
+
noise: 0.1 # Aggiunto rumore per ulteriore variabilità
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2
|
3 |
+
size 1089994880
|
model-00002-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26cac15f69a0986aa527db661257174afd8c6cc8ccb4e937bdedfaad76775ed4
|
3 |
+
size 1089994896
|
model-00003-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3fca0545f38f5c06dfcab0739750941ade6e693cced38a0403bc509e4eb6b400
|
3 |
+
size 466124232
|
model-00004-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55d98c019219ff1ebc4b9bf0b2b65bfe3fbe202666e1ded188b2cd7ec653e1f7
|
3 |
+
size 466116968
|
model-00005-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c35d6228b3516539bf0df0a4c633b16cfba2b3561762389dfd014c684ae23bde
|
3 |
+
size 466116976
|
model-00006-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27c2b6ec8794896c43dfde7ed22ab88fbe061996948087582b4b02807256ddef
|
3 |
+
size 466116976
|
model-00007-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:098d743edf9e479f3ec7800cfe58e42f396ce7c3f203b6484bdae6fa101d3f21
|
3 |
+
size 466116976
|
model-00008-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:717da87ae15723328717b58ac9ce23f14d1a27d6903de97e06bcae71db976499
|
3 |
+
size 466116976
|
model-00009-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a10cc6824a7021329e6473e30d21a6b504d69baaaac81118f6b2f6b17458de9
|
3 |
+
size 466116976
|
model-00010-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52f07d169c1bb08f3c2cad71e8c179b06eab94eb07ad526eba51c22d9c5b621d
|
3 |
+
size 466116976
|
model-00011-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:468416bff0e25aae78676b0cc9418d9e8dcc16a94c5249e878df9de26d008f3d
|
3 |
+
size 466116976
|
model-00012-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cd50b815c5edc7a568b9d0b0048fc7256f7fa0e1887ebdfffa9ff6b4a6dae0e
|
3 |
+
size 466116976
|
model-00013-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6dc10cc5ac81a329c0949446c8835966be3634322d97ed20063e76bfdd80972
|
3 |
+
size 466116976
|
model-00014-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c65a74d4b963f8201e0e843da95befb2591840b5100662e9669e93ebd37a4004
|
3 |
+
size 466116976
|
model-00015-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56c32c06d951e81f25cc808f6d04720cecdb51d0888d6a601a1e28aa98761573
|
3 |
+
size 466116968
|
model-00016-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:145f90946a4777ad4b14e4738ced52542033ac822950633be510241fcfe247fe
|
3 |
+
size 466116976
|
model-00017-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:208d3b337871ddc1958e95e113d671952d31fe40f26d280cb855c145e6902a1e
|
3 |
+
size 466116976
|
model-00018-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc88fab4c7734c4a20cd781319d4ab452dc71fba20ae1c6d835028e6b093a8a1
|
3 |
+
size 466116976
|
model-00019-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07cad6ca2483bafd239ca86a234a39045b5e8f7e8b56fa80c471dbbab9744cb3
|
3 |
+
size 466116976
|
model-00020-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:330117964957106396a52f0cd0d18ca4ec5669374ced8d4c168241af2427b5ca
|
3 |
+
size 466116976
|
model-00021-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3998404659053d59a936af8b1f869c8491a2dca2c788d61a3e60e981fd1f2a44
|
3 |
+
size 466116976
|
model-00022-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e901abda39a2868e3a88d3f45ba6d762a6dce598f59481344c872f881b4d666c
|
3 |
+
size 466116976
|
model-00023-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eb905574bb86af277a98fc76261bd0dcabdbbeae6e9ee1d86be1b6e0ecdd01f
|
3 |
+
size 466116976
|
model-00024-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8270c4481e1ab43ae2d8915cde377ef21f6737082a25b905c1d2cd4b6ccbc354
|
3 |
+
size 466116960
|
model-00025-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a48f6265965f448a3f8d756b3e7a1370b2c32bb27a9d55d02f1b30937704afb
|
3 |
+
size 466116960
|
model-00026-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c872d8ed72f356db36b577cf5f3c5f13abd896aab35193e52b17e7d8f3df94d9
|
3 |
+
size 466116960
|
model-00027-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b06dfcdd48f94a649c548e3cbd7c1988530e021d058f1caf9cbe4abbfc80685f
|
3 |
+
size 466116960
|
model-00028-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1aed58be1726ed2770eeea49666eb3fa530e79234be822a555a4edc0e8682ad
|
3 |
+
size 466116960
|
model-00029-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b653009f3c7e6a1269abc98448343d7b5684cb982d0a006efcac2670f6e129f7
|
3 |
+
size 466116960
|
model-00030-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5312750c9cb28a9103fd9c273d402ddaeaa22b939c8fa9ed1ad194f009df8a6
|
3 |
+
size 466116944
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15231233024}, "weight_map": {"lm_head.weight": "model-00001-of-00030.safetensors", "model.embed_tokens.weight": "model-00002-of-00030.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.2.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.21.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.22.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.3.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.7.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.8.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.9.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.norm.weight": "model-00030-of-00030.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 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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 |
+
"model_max_length": 131072,
|
203 |
+
"pad_token": "<|endoftext|>",
|
204 |
+
"split_special_tokens": false,
|
205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
206 |
+
"unk_token": null
|
207 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|