Upload folder using huggingface_hub
Browse files- README.md +37 -0
- added_tokens.json +5 -0
- config.json +30 -0
- mergekit_config.yml +7 -0
- merges.txt +0 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +40 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- 01-ai/Yi-1.5-34B-Chat
|
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 [linear](https://arxiv.org/abs/2203.05482) merge method.
|
18 |
+
|
19 |
+
### Models Merged
|
20 |
+
|
21 |
+
The following models were included in the merge:
|
22 |
+
* [01-ai/Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat)
|
23 |
+
|
24 |
+
### Configuration
|
25 |
+
|
26 |
+
The following YAML configuration was used to produce this model:
|
27 |
+
|
28 |
+
```yaml
|
29 |
+
models:
|
30 |
+
- model: 01-ai/Yi-1.5-34B-Chat
|
31 |
+
parameters:
|
32 |
+
weight: 1.0
|
33 |
+
merge_method: linear
|
34 |
+
dtype: bfloat16
|
35 |
+
tokenizer_source: model:Qwen/Qwen-tokenizer
|
36 |
+
|
37 |
+
```
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "01-ai/Yi-1.5-34B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 56,
|
18 |
+
"num_hidden_layers": 60,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 5000000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.41.0",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 151646
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: 01-ai/Yi-1.5-34B-Chat
|
3 |
+
parameters:
|
4 |
+
weight: 1.0
|
5 |
+
merge_method: linear
|
6 |
+
dtype: bfloat16
|
7 |
+
tokenizer_source: model:Qwen/Qwen-tokenizer
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35114771ea8ca9330b0ba6f5c0f84085d7aa9250995c65e8dd45e1c15badb904
|
3 |
+
size 4961950664
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7229365d120c52821635664a94f19c4f8c9fc3f7eccecde829c19d9b5347bf86
|
3 |
+
size 4976675528
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91190a6bcd4d7f9383f998dd094bbc31d4c96e700e879c34fb1080b565d493fe
|
3 |
+
size 4756459760
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a08b8d2fc13b409ad11a79799d0d6de922f23225b8c3d9caa921206994c7f715
|
3 |
+
size 4991370152
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e648aadc7e7156c0610cec0aba1a8f71aac2208097d725a1bbfde482a0a8e6
|
3 |
+
size 4756459768
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f002f7116420b9579cd744433b67862d37ce6d3533ae7572d9ce91a263f4e6f3
|
3 |
+
size 4756459752
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1465c4fa995e4feecccc0fe602a190d971fc074c40d5801c90063d5d0550d2f
|
3 |
+
size 4991370160
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5159094759a3d0aefd2d501878c7f07af15b24db4cfd45700674fef10f36d8d6
|
3 |
+
size 4756459768
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38684c24da9be33f783f78e23210c774b850ba1749824f5b278134272d547b57
|
3 |
+
size 4756459752
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57cd747a832eaccf32ba5baf765a6e7ba0c84b0af91a439fcd4d20450c4861a1
|
3 |
+
size 4991370160
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c362be47b7473af966380735b3fba5dc7fc9a425ebbf3300edcd6fd14a4e1e
|
3 |
+
size 4756459760
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2848a11f278e0c00696870d52d0bc62b3822f6dd34e568d03b2c8e9aa5fca731
|
3 |
+
size 4756459760
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4fb6b9f1be86463a4b706f4db675a8cd08a8fb417e1c847fd35c08435203e94
|
3 |
+
size 4991370160
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96b6a7c37ca401bd3ad79cb202a4d35a0d5dfc181a0aa9b56603c7ce9657e4d3
|
3 |
+
size 4756459736
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56902f0829cff3c5055acc6cbdcde107ad89eb11a6e0a62bbdc701f848b75186
|
3 |
+
size 822113184
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 68777834496}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<|endoftext|>",
|
31 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "<|endoftext|>",
|
34 |
+
"errors": "replace",
|
35 |
+
"model_max_length": 32768,
|
36 |
+
"pad_token": "<|endoftext|>",
|
37 |
+
"split_special_tokens": false,
|
38 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
39 |
+
"unk_token": null
|
40 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|