Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +58 -0
- added_tokens.json +24 -0
- config.json +29 -0
- mergekit_config.yml +27 -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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- win10/Urdandi-Qwen2.5-7B
|
4 |
+
- Qwen/Qwen2.5-Coder-7B
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# merge
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) as a base.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [win10/Urdandi-Qwen2.5-7B](https://huggingface.co/win10/Urdandi-Qwen2.5-7B)
|
24 |
+
|
25 |
+
### Configuration
|
26 |
+
|
27 |
+
The following YAML configuration was used to produce this model:
|
28 |
+
|
29 |
+
```yaml
|
30 |
+
models:
|
31 |
+
- model: win10/Urdandi-Qwen2.5-7B
|
32 |
+
parameters:
|
33 |
+
density: 1
|
34 |
+
weight: 1
|
35 |
+
|
36 |
+
- model: Qwen/Qwen2.5-Coder-7B
|
37 |
+
parameters:
|
38 |
+
density: 1
|
39 |
+
weight: 1
|
40 |
+
|
41 |
+
- model: win10/Urdandi-Qwen2.5-7B
|
42 |
+
parameters:
|
43 |
+
density: 1
|
44 |
+
weight: 1
|
45 |
+
|
46 |
+
- model: Qwen/Qwen2.5-Coder-7B
|
47 |
+
parameters:
|
48 |
+
density: 1
|
49 |
+
weight: 1
|
50 |
+
|
51 |
+
merge_method: ties
|
52 |
+
base_model: Qwen/Qwen2.5-Coder-7B
|
53 |
+
parameters:
|
54 |
+
normalize: true
|
55 |
+
int8_mask: true
|
56 |
+
dtype: bfloat16
|
57 |
+
|
58 |
+
```
|
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",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
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 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: win10/Urdandi-Qwen2.5-7B
|
3 |
+
parameters:
|
4 |
+
density: 1
|
5 |
+
weight: 1
|
6 |
+
|
7 |
+
- model: Qwen/Qwen2.5-Coder-7B
|
8 |
+
parameters:
|
9 |
+
density: 1
|
10 |
+
weight: 1
|
11 |
+
|
12 |
+
- model: win10/Urdandi-Qwen2.5-7B
|
13 |
+
parameters:
|
14 |
+
density: 1
|
15 |
+
weight: 1
|
16 |
+
|
17 |
+
- model: Qwen/Qwen2.5-Coder-7B
|
18 |
+
parameters:
|
19 |
+
density: 1
|
20 |
+
weight: 1
|
21 |
+
|
22 |
+
merge_method: ties
|
23 |
+
base_model: Qwen/Qwen2.5-Coder-7B
|
24 |
+
parameters:
|
25 |
+
normalize: true
|
26 |
+
int8_mask: true
|
27 |
+
dtype: bfloat16
|
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:db2e7e72074ccde3b1ba9a77de27007bcedebd0dba32cf60fd2223bd965ee11c
|
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:d195febfea337302ad5b85fc55a80e978927f3f7aa1d9b202f7b586d4ca9cd7f
|
3 |
+
size 1089994896
|
model-00003-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01a4bd276d9995c0941bad82e2a6f5dbd0b4827bd69ee3efe58b808379210ea6
|
3 |
+
size 466124232
|
model-00004-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:390731ee5d18a38ea1876d1d0b99e627d12838df61db375b4411d7ddc6cce26a
|
3 |
+
size 466116968
|
model-00005-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3abde059ad4f7561b96d6895dfd060540b55ec5b76dac198ba71552ca7d31485
|
3 |
+
size 466116976
|
model-00006-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f3cc477a5455075df8b06d67b73e5446a4cb15a7ba434578d53d78b977d0608
|
3 |
+
size 466116976
|
model-00007-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:866d7d2a9feb65a7e256217ededbf6453e1e4e0ca0098df3e93668a5912ede57
|
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:bc00bd102fe51948290a06b241d83d5b3dc9b1642d4b38541fa95873b9b74531
|
3 |
+
size 466116976
|
model-00009-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57aa69776886b8ea9697aa2ab8fbe7a322fda33b5554f53e2534d71cf9e638df
|
3 |
+
size 466116976
|
model-00010-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ca4c84a4f089c40fc03c20a70befff0180aa365eac0844a23851690c15674c7
|
3 |
+
size 466116976
|
model-00011-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dc5ea819b9ef15c86e6c642f5933d8f94ea29ea08280281b440ab6cc3de1e3a
|
3 |
+
size 466116976
|
model-00012-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3656f745a995aea00325063f5139e0778cfc88dcf3ed45d142e0237483eebad6
|
3 |
+
size 466116976
|
model-00013-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99477a29479a22a69739529b82004c6bc181faba59d1e5d5347be781152c1082
|
3 |
+
size 466116976
|
model-00014-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb4513165e95af26bc9dcd348184593bae2a478f0065429f64d423b20dd28dc
|
3 |
+
size 466116976
|
model-00015-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40026b696a335307a3bb37e7877f37ba968268597c7beb52cef045e048852c55
|
3 |
+
size 466116968
|
model-00016-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f0ecf76e986dd7c8a4bb2f92cc7920c7bcee955dc5b772070180424b16ae55
|
3 |
+
size 466116976
|
model-00017-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3160c3391f075661779aff334dfd0446ff0f57eb04273c1d0c232a86e1dc46ed
|
3 |
+
size 466116976
|
model-00018-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d28ff4a6fd856fb3fcceabbe5214a413ec4fef7da0e9ab13ce527f37676242b
|
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:a8905c669315bf553a6ea0874a70ef6535e136e2dd4beb04a0de6d7756946350
|
3 |
+
size 466116976
|
model-00020-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65a119703e568055a6e355f73b5505635a476b973e6bdf057a3d6ed3eec294d4
|
3 |
+
size 466116976
|
model-00021-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f91231538efe7c968df9562aced7562b4b4ec3e4fb14631c0ac2e891b9b53fd
|
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:ecef5c9b1b0524586487461db3337ebb1b1d959b8a2938a48f280b0f8751d893
|
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:ece73b0202a6830b1946ffd5e14b3bd538cd755333adbfebb5344b0388800c15
|
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:d52956d218758f7e080dbbaf274d00598e120b8201dbf77529491a4d71ec66ad
|
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:b42e96cdef493a9925ca2a36047c782ab59fb2738d91c21b2cc70a5a3c9e4b22
|
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:d38fbd6926d80ed7a3d42a181841a998d27ccda121075925e35c5a20bb12300f
|
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:c9463553bee90366ce0faeb0a005a6c43942c3caeea0491c2513f1f51af92d55
|
3 |
+
size 466116960
|
model-00028-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dbaacdf52a6237036a1d88facd05ffc3d0e0a9a0e98f5e425eac53522f0d854
|
3 |
+
size 466116960
|
model-00029-of-00030.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02a0fd3c65ebbe59636b63c2ab200c7b659dc2e64b09928c6d53fe8cba21cd09
|
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:c9ab3bcb3ed48b266d05545bca3c16c591ba0f43e2580074d152a56c565a9be1
|
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": "<|endoftext|>",
|
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": "<|endoftext|>",
|
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
|
|