allknowingroger
commited on
Commit
•
890db39
1
Parent(s):
433cb13
Upload folder using huggingface_hub
Browse files- README.md +39 -0
- added_tokens.json +5 -0
- config.json +27 -0
- mergekit_config.yml +9 -0
- merges.txt +0 -0
- model-00001-of-00027.safetensors +3 -0
- model-00002-of-00027.safetensors +3 -0
- model-00003-of-00027.safetensors +3 -0
- model-00004-of-00027.safetensors +3 -0
- model-00005-of-00027.safetensors +3 -0
- model-00006-of-00027.safetensors +3 -0
- model-00007-of-00027.safetensors +3 -0
- model-00008-of-00027.safetensors +3 -0
- model-00009-of-00027.safetensors +3 -0
- model-00010-of-00027.safetensors +3 -0
- model-00011-of-00027.safetensors +3 -0
- model-00012-of-00027.safetensors +3 -0
- model-00013-of-00027.safetensors +3 -0
- model-00014-of-00027.safetensors +3 -0
- model-00015-of-00027.safetensors +3 -0
- model-00016-of-00027.safetensors +3 -0
- model-00017-of-00027.safetensors +3 -0
- model-00018-of-00027.safetensors +3 -0
- model-00019-of-00027.safetensors +3 -0
- model-00020-of-00027.safetensors +3 -0
- model-00021-of-00027.safetensors +3 -0
- model-00022-of-00027.safetensors +3 -0
- model-00023-of-00027.safetensors +3 -0
- model-00024-of-00027.safetensors +3 -0
- model-00025-of-00027.safetensors +3 -0
- model-00026-of-00027.safetensors +3 -0
- model-00027-of-00027.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- MaziyarPanahi/calme-2.4-rys-78b
|
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 passthrough merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [MaziyarPanahi/calme-2.4-rys-78b](https://huggingface.co/MaziyarPanahi/calme-2.4-rys-78b)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
slices:
|
30 |
+
- sources:
|
31 |
+
- model: MaziyarPanahi/calme-2.4-rys-78b
|
32 |
+
layer_range: [0, 39]
|
33 |
+
- sources:
|
34 |
+
- model: MaziyarPanahi/calme-2.4-rys-78b
|
35 |
+
layer_range: [8, 39]
|
36 |
+
merge_method: passthrough
|
37 |
+
dtype: float16
|
38 |
+
|
39 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MaziyarPanahi/calme-2.4-rys-78b",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"eos_token_id": 151645,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 8192,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 29568,
|
12 |
+
"max_position_embeddings": 32768,
|
13 |
+
"max_window_layers": 80,
|
14 |
+
"model_type": "qwen2",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_hidden_layers": 70,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-06,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.44.1",
|
24 |
+
"use_cache": false,
|
25 |
+
"use_sliding_window": false,
|
26 |
+
"vocab_size": 151646
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
- sources:
|
3 |
+
- model: MaziyarPanahi/calme-2.4-rys-78b
|
4 |
+
layer_range: [0, 39]
|
5 |
+
- sources:
|
6 |
+
- model: MaziyarPanahi/calme-2.4-rys-78b
|
7 |
+
layer_range: [8, 39]
|
8 |
+
merge_method: passthrough
|
9 |
+
dtype: float16
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a91a15a9bed33520c4b2da36931044d8a0e6a239291bf76ae5bf45ebbec24a57
|
3 |
+
size 4969152856
|
model-00002-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f9447db4ed8dac7a7b5c5839c347a0036d11ee08f20cf240ae005530e4f818b
|
3 |
+
size 4964084872
|
model-00003-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a495f0597583d055d913e2ebfc1b01630d73362485d2109bc1f7cba50447c6ef
|
3 |
+
size 4997660376
|
model-00004-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8e2e4e93a2938a81e3219380d28d5cf7cc03e55922d9d61517c1e7b1b8ab0b8
|
3 |
+
size 4565680272
|
model-00005-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a9a7645150c0bd50a8035412943b3591a77c525691e62dec0256f3b05aa1ec9
|
3 |
+
size 4964068400
|
model-00006-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b9f570faa864a445b45d558ea72b521f20213254ad99dde36e69080af3def3f
|
3 |
+
size 4915904664
|
model-00007-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe90e43c6984a3a2bfb74f9210628be93cc18b5f848f3047521a6b67070099f3
|
3 |
+
size 4647435984
|
model-00008-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a51994e2ca98b91f5b2d7ed7ab15817ff072d1cb4a6904993951ccea7f391c4a
|
3 |
+
size 4964068392
|
model-00009-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4002f5e3fbad1ceb012a3915ec0aa5554adcfd7d7b7233af6843096cc84fedc2
|
3 |
+
size 4599255760
|
model-00010-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:546c34e4e7ea83a5a21b23a04df8646613924afddcabd5379d85248b311522fd
|
3 |
+
size 4964101384
|
model-00011-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:528458bae6d7f60ee4f292b365af5c0c1b65d8e2f1b8d4cb7bfe383423758f87
|
3 |
+
size 4781653832
|
model-00012-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:896b56885429d2d228517368ddb476f74ab744e1f13b6d0667c4a33ca770d393
|
3 |
+
size 4964068392
|
model-00013-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f6f7f4edab7c1e836dce9912354078d0a16be934bac1644b548a32e76279d74
|
3 |
+
size 4599272256
|
model-00014-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a68dd855a6c59f1224a89659ccd368c3e6cd8771bf241310cd57e7d6c59ebe6
|
3 |
+
size 4964068400
|
model-00015-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a71e8ee659f7ea17fbc6013c654aa15c7f6b3a2251f2a12dd1132be871a46002
|
3 |
+
size 4997660376
|
model-00016-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bb0ba2700e817b9a263d1d0c6e78682fe0310d8da1f92884eeabc3ac733363d
|
3 |
+
size 4565680272
|
model-00017-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:401671ace914e220a5ba94c4917538716383d00884128750317fe48002f5108b
|
3 |
+
size 4781670320
|
model-00018-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b6bf5f67361479d892356f86d9c7fc92cca93556ca3546be287bb06e5a5087
|
3 |
+
size 4964068400
|
model-00019-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9c8414ce77fb5b6f854f815428a0911d89c1a8e0a4d9ab0e1d085d5ed348751
|
3 |
+
size 4997660376
|
model-00020-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:773e99cb6f2840a3d01b6c041901a947df1fe7a2350ebca6da7757d770ec45c5
|
3 |
+
size 4565680272
|
model-00021-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ca8a745b5893e42cd40ac65dbf41d769f248450b289510c257b48a02605f70f
|
3 |
+
size 4964068400
|
model-00022-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf70a3552940265d6f339d41096907ce5cf698bd5bd9c060c844b17fe4a3197e
|
3 |
+
size 4915904664
|
model-00023-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df9d8c39bda5d2d822827ede3fbae7998df41900396bee79892e7002130e8f0e
|
3 |
+
size 4647435984
|
model-00024-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea02dfe66fe4bd3d55424304a2e6a124490599af2266585f98a3db9a95e383a1
|
3 |
+
size 4781653824
|
model-00025-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e24a9b95ca8c4f15fa3b738d88d87db4f284f792ce0a00d3c33df8b2fa2095a
|
3 |
+
size 4781686776
|
model-00026-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:291592d75b41d99a2c744dfeeba6e24015ef97f0d99b0954bf35561e487dd2db
|
3 |
+
size 4964068384
|
model-00027-of-00027.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a144ee5961829d090b90bd9ecaab8114b9f65302171942257433f3a69ca41269
|
3 |
+
size 2057398496
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 127845015552}, "weight_map": {"lm_head.weight": "model-00001-of-00027.safetensors", "model.embed_tokens.weight": "model-00001-of-00027.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00027.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00027.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00027.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00027.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00027.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00027.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00027.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00027.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00027.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.input_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00027.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00027.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00027.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00027.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00027.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00027.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00005-of-00027.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.input_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00027.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00027.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00027.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00027.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00027.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00027.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00027.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00027.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00027.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00027.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00027.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00027.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00027.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00027.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00027.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00027.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00010-of-00027.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00027.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.21.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00027.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00027.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00027.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00027.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00027.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00027.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00027.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00012-of-00027.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.24.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00027.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00027.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00027.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00027.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00014-of-00027.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00027.safetensors", "model.layers.57.input_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00027.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00027.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00014-of-00027.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00015-of-00027.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00027.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.input_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.27.input_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00027.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00016-of-00027.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00027.safetensors", "model.layers.60.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00027.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00016-of-00027.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00017-of-00027.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00027.safetensors", "model.layers.61.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00027.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00018-of-00027.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00018-of-00027.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00027.safetensors", "model.layers.62.input_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.31.input_layernorm.weight": "model-00018-of-00027.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00027.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00018-of-00027.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00019-of-00027.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00019-of-00027.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.input_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.32.input_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00027.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.33.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00020-of-00027.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00027.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00027.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00020-of-00027.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00021-of-00027.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00021-of-00027.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.input_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.35.input_layernorm.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00027.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00022-of-00027.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00022-of-00027.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.input_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.36.input_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00022-of-00027.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00022-of-00027.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.37.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00023-of-00027.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00023-of-00027.safetensors", "model.layers.69.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.38.input_layernorm.weight": "model-00023-of-00027.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00023-of-00027.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00024-of-00027.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00027.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00027.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00024-of-00027.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00025-of-00027.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00027.safetensors", "model.layers.39.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.8.input_layernorm.weight": "model-00025-of-00027.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00026-of-00027.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00026-of-00027.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00026-of-00027.safetensors", "model.layers.40.input_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.9.input_layernorm.weight": "model-00026-of-00027.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00026-of-00027.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00026-of-00027.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00027-of-00027.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00027-of-00027.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00027-of-00027.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00027-of-00027.safetensors", "model.norm.weight": "model-00027-of-00027.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 131072,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|