Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +48 -0
- config.json +34 -0
- generation_config.json +8 -0
- mergekit_config.yml +14 -0
- model-00001-of-00024.safetensors +3 -0
- model-00002-of-00024.safetensors +3 -0
- model-00003-of-00024.safetensors +3 -0
- model-00004-of-00024.safetensors +3 -0
- model-00005-of-00024.safetensors +3 -0
- model-00006-of-00024.safetensors +3 -0
- model-00007-of-00024.safetensors +3 -0
- model-00008-of-00024.safetensors +3 -0
- model-00009-of-00024.safetensors +3 -0
- model-00010-of-00024.safetensors +3 -0
- model-00011-of-00024.safetensors +3 -0
- model-00012-of-00024.safetensors +3 -0
- model-00013-of-00024.safetensors +3 -0
- model-00014-of-00024.safetensors +3 -0
- model-00015-of-00024.safetensors +3 -0
- model-00016-of-00024.safetensors +3 -0
- model-00017-of-00024.safetensors +3 -0
- model-00018-of-00024.safetensors +3 -0
- model-00019-of-00024.safetensors +3 -0
- model-00020-of-00024.safetensors +3 -0
- model-00021-of-00024.safetensors +3 -0
- model-00022-of-00024.safetensors +3 -0
- model-00023-of-00024.safetensors +3 -0
- model-00024-of-00024.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +34 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- anthracite-core/magnum-v3-27b-kto-r3
|
4 |
+
- anthracite-core/magnum-v3-27b-KTO-e1-r2
|
5 |
+
- anthracite-core/magnum-v3-27b-KTO-e0.25-r1
|
6 |
+
- IntervitensInc/gemma-2-27b-chatml
|
7 |
+
library_name: transformers
|
8 |
+
tags:
|
9 |
+
- mergekit
|
10 |
+
- merge
|
11 |
+
|
12 |
+
---
|
13 |
+
# output8
|
14 |
+
|
15 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
16 |
+
|
17 |
+
## Merge Details
|
18 |
+
### Merge Method
|
19 |
+
|
20 |
+
This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [IntervitensInc/gemma-2-27b-chatml](https://huggingface.co/IntervitensInc/gemma-2-27b-chatml) as a base.
|
21 |
+
|
22 |
+
### Models Merged
|
23 |
+
|
24 |
+
The following models were included in the merge:
|
25 |
+
* [anthracite-core/magnum-v3-27b-kto-r3](https://huggingface.co/anthracite-core/magnum-v3-27b-kto-r3)
|
26 |
+
* [anthracite-core/magnum-v3-27b-KTO-e1-r2](https://huggingface.co/anthracite-core/magnum-v3-27b-KTO-e1-r2)
|
27 |
+
* [anthracite-core/magnum-v3-27b-KTO-e0.25-r1](https://huggingface.co/anthracite-core/magnum-v3-27b-KTO-e0.25-r1)
|
28 |
+
|
29 |
+
### Configuration
|
30 |
+
|
31 |
+
The following YAML configuration was used to produce this model:
|
32 |
+
|
33 |
+
```yaml
|
34 |
+
base_model: IntervitensInc/gemma-2-27b-chatml
|
35 |
+
dtype: float32
|
36 |
+
merge_method: task_arithmetic
|
37 |
+
models:
|
38 |
+
- model: IntervitensInc/gemma-2-27b-chatml
|
39 |
+
- model: anthracite-core/magnum-v3-27b-KTO-e0.25-r1
|
40 |
+
parameters:
|
41 |
+
weight: 0.5
|
42 |
+
- model: anthracite-core/magnum-v3-27b-KTO-e1-r2
|
43 |
+
parameters:
|
44 |
+
weight: 0.1
|
45 |
+
- model: anthracite-core/magnum-v3-27b-kto-r3
|
46 |
+
parameters:
|
47 |
+
weight: 0.4
|
48 |
+
```
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Gemma2ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"attn_logit_softcapping": 50.0,
|
8 |
+
"bos_token_id": 2,
|
9 |
+
"cache_implementation": "hybrid",
|
10 |
+
"eos_token_id": 8,
|
11 |
+
"final_logit_softcapping": 30.0,
|
12 |
+
"head_dim": 128,
|
13 |
+
"hidden_act": "gelu_pytorch_tanh",
|
14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
15 |
+
"hidden_size": 4608,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 36864,
|
18 |
+
"max_position_embeddings": 8192,
|
19 |
+
"model_type": "gemma2",
|
20 |
+
"num_attention_heads": 32,
|
21 |
+
"num_hidden_layers": 46,
|
22 |
+
"num_key_value_heads": 16,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"query_pre_attn_scalar": 144,
|
25 |
+
"rms_norm_eps": 1e-06,
|
26 |
+
"rope_theta": 10000.0,
|
27 |
+
"sliding_window": 4096,
|
28 |
+
"sliding_window_size": 4096,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.42.0.dev0",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 256000,
|
33 |
+
"_attn_implementation": "eager"
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"cache_implementation": "hybrid",
|
5 |
+
"eos_token_id": 8,
|
6 |
+
"pad_token_id": 0,
|
7 |
+
"transformers_version": "4.42.0.dev0"
|
8 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: IntervitensInc/gemma-2-27b-chatml
|
2 |
+
dtype: float32
|
3 |
+
merge_method: task_arithmetic
|
4 |
+
models:
|
5 |
+
- model: IntervitensInc/gemma-2-27b-chatml
|
6 |
+
- model: anthracite-core/magnum-v3-27b-KTO-e0.25-r1
|
7 |
+
parameters:
|
8 |
+
weight: 0.5
|
9 |
+
- model: anthracite-core/magnum-v3-27b-KTO-e1-r2
|
10 |
+
parameters:
|
11 |
+
weight: 0.1
|
12 |
+
- model: anthracite-core/magnum-v3-27b-kto-r3
|
13 |
+
parameters:
|
14 |
+
weight: 0.4
|
model-00001-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f20a339226b26c42177e1ebad425e677fd6df88f73d012711f5c4265cba87ced
|
3 |
+
size 4718610680
|
model-00002-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40825913a614b9bbc050ee6cabd65337b43d5594f448a83342b54fa79f4416d2
|
3 |
+
size 4529998360
|
model-00003-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1995347cbad214030e684be6bbec3fc657a174b445e3d3efa41aecaaf317ab07
|
3 |
+
size 4529998376
|
model-00004-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f33a0fb153fd74adb5f735de04144a4c68c6e00fe4f863277e2238279b7c5c0
|
3 |
+
size 4529998376
|
model-00005-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322a199ed75f5cf57228e515f08b29342a5987fb37bd40c0e0f36f16515cc7b2
|
3 |
+
size 4529998376
|
model-00006-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5bf1eb527eed57617c21951cdd555c01f71f1e986d5372dd991e6571f4ce283
|
3 |
+
size 4529998376
|
model-00007-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa174592682844274d009bad17a163b43d4e27d27875a9c6ec4278e7c8a715a4
|
3 |
+
size 4529998376
|
model-00008-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abc8fe40bf741d79df5ef1541d2743a3b6a6d57dac30d386dc3dd59746d548b0
|
3 |
+
size 4529998368
|
model-00009-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff1da007faaaf00d63afc5a8067fd4a17de78f067cfc5d9f87f8d83647c6bdd5
|
3 |
+
size 4529998376
|
model-00010-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3554a9b1066c08bd12c9edeb6f53dcd16821c774d84cbd81776819e10b18f9c5
|
3 |
+
size 4529998376
|
model-00011-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ecb271470c62192d7295cad354319ccdf7b0cf83153c2cab4f674f59b91e4b0
|
3 |
+
size 4529998376
|
model-00012-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a5e618195db30d730fd53952b695d0da17ef08d6078d8fdb9680ce36723f928
|
3 |
+
size 4529998376
|
model-00013-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e02cbc2cffb5b40ea1eee002f91c9132d004de76a77d1b46b6da3f8dbcf9cfba
|
3 |
+
size 4529998368
|
model-00014-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5721933818f9b9dfa2b417ec11c82cc55975ed060faaee922d053f659c43dabf
|
3 |
+
size 4529998376
|
model-00015-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c343cfd94457f5a8e1699836c78a6a75e677817da4ef2c9bd091c4c75fdb6518
|
3 |
+
size 4529998376
|
model-00016-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98da8ea350588f8a7263810ef9937cc2d8b62df1c3e48bbc7a5b649e28b7af43
|
3 |
+
size 4529998376
|
model-00017-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:929342fd98af21da535e97f0eea2e56a893b6e63ace9e6ca8f36414fb53c9945
|
3 |
+
size 4529998376
|
model-00018-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6e86a934f71c89634e49b88c6a7e1d164ec7f3c4061def3c62dca8b1379e0b4
|
3 |
+
size 4529998376
|
model-00019-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e33d0661dfa3d61ea5aadbabcaf0cc7ff973cd06f69d2d302ae2d2532338250
|
3 |
+
size 4529998368
|
model-00020-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72b5e009a1fabae323baf0bd7d7cd32e59558712c9271e9ae0cdeedddc2011e5
|
3 |
+
size 4529998376
|
model-00021-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b854820f97ea3ee713dee5788fd276fc7c0a8210c7114dabe28ef16599df1450
|
3 |
+
size 4529998376
|
model-00022-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e744cca14032308c6b0e4a023662c73306fea847a49af9083ed850dfd3c667b3
|
3 |
+
size 4529998368
|
model-00023-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4f0ed40f8ae520fda556ae91064598ccc92d53e92d7f814ec65e98e4ede69bc
|
3 |
+
size 4529998360
|
model-00024-of-00024.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:756be5109f31dc0630276e3c17f80f5cf6a9305a128a52a4cfca5f70df8cfe9e
|
3 |
+
size 4529998336
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 108908513280}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00024.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.0.post_feedforward_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.0.pre_feedforward_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.10.post_feedforward_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.10.pre_feedforward_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.11.post_feedforward_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.11.pre_feedforward_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.12.post_feedforward_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.12.pre_feedforward_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.13.post_feedforward_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.13.pre_feedforward_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.14.post_feedforward_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.14.pre_feedforward_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.15.post_feedforward_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.15.pre_feedforward_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.16.post_feedforward_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.16.pre_feedforward_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.17.post_feedforward_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.17.pre_feedforward_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.18.post_feedforward_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.18.pre_feedforward_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.19.post_feedforward_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.19.pre_feedforward_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.2.post_feedforward_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.2.pre_feedforward_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.20.post_feedforward_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.20.pre_feedforward_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.21.post_feedforward_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.21.pre_feedforward_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.22.post_feedforward_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.22.pre_feedforward_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.23.post_feedforward_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.23.pre_feedforward_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.24.post_feedforward_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.24.pre_feedforward_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.25.post_feedforward_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.25.pre_feedforward_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.26.post_feedforward_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.26.pre_feedforward_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.27.post_feedforward_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.27.pre_feedforward_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.28.post_feedforward_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.28.pre_feedforward_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.29.post_feedforward_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.29.pre_feedforward_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.3.post_feedforward_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.3.pre_feedforward_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.30.post_feedforward_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.30.pre_feedforward_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.31.post_feedforward_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.31.pre_feedforward_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.32.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.32.post_feedforward_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.32.pre_feedforward_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.33.post_feedforward_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.33.pre_feedforward_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.34.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.34.post_feedforward_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.34.pre_feedforward_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.35.post_feedforward_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.35.pre_feedforward_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.36.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.36.post_feedforward_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.36.pre_feedforward_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.37.post_feedforward_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.37.pre_feedforward_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.38.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.38.post_feedforward_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.38.pre_feedforward_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.39.post_feedforward_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.39.pre_feedforward_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.4.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.4.post_feedforward_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.4.pre_feedforward_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.40.post_feedforward_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.40.pre_feedforward_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.41.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.41.post_feedforward_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.41.pre_feedforward_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.42.post_feedforward_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.42.pre_feedforward_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.43.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.43.post_feedforward_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.43.pre_feedforward_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.44.post_feedforward_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.44.pre_feedforward_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.45.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.45.post_feedforward_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.45.pre_feedforward_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.post_feedforward_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.pre_feedforward_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.6.post_feedforward_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.6.pre_feedforward_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.7.post_feedforward_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.7.pre_feedforward_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.8.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.8.post_feedforward_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.8.pre_feedforward_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.input_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.9.post_feedforward_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.9.pre_feedforward_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.norm.weight": "model-00024-of-00024.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<start_of_turn>",
|
4 |
+
"<end_of_turn>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<bos>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<pad>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66c28a230d9e5c840e83aeedfcb553006011db12dbc58aa20cc7e515bc1309cc
|
3 |
+
size 17518532
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01f545c6099874ce0c5cf6e4ccecd5f2bce689852b576ddf9d49134081c9cb98
|
3 |
+
size 4241007
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37261851a5317f74bb796a7c5965f67e1e6bfb2c62e37ff6f61d3b90a361b681
|
3 |
+
size 17518528
|