Upload folder using huggingface_hub
Browse files- README.md +47 -0
- config.json +30 -0
- mergekit_config.yml +8 -0
- model-00001-of-00022.safetensors +3 -0
- model-00002-of-00022.safetensors +3 -0
- model-00003-of-00022.safetensors +3 -0
- model-00004-of-00022.safetensors +3 -0
- model-00005-of-00022.safetensors +3 -0
- model-00006-of-00022.safetensors +3 -0
- model-00007-of-00022.safetensors +3 -0
- model-00008-of-00022.safetensors +3 -0
- model-00009-of-00022.safetensors +3 -0
- model-00010-of-00022.safetensors +3 -0
- model-00011-of-00022.safetensors +3 -0
- model-00012-of-00022.safetensors +3 -0
- model-00013-of-00022.safetensors +3 -0
- model-00014-of-00022.safetensors +3 -0
- model-00015-of-00022.safetensors +3 -0
- model-00016-of-00022.safetensors +3 -0
- model-00017-of-00022.safetensors +3 -0
- model-00018-of-00022.safetensors +3 -0
- model-00019-of-00022.safetensors +3 -0
- model-00020-of-00022.safetensors +3 -0
- model-00021-of-00022.safetensors +3 -0
- model-00022-of-00022.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +45 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
---
|
7 |
+
|
8 |
+
# chimera-ggobugi-solar-v1
|
9 |
+
|
10 |
+
chimera-ggobugi-solar-v1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
11 |
+
|
12 |
+
## 🧩 Configuration
|
13 |
+
|
14 |
+
```yaml
|
15 |
+
models:
|
16 |
+
- model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
|
17 |
+
- model: MoaData/Myrrh_solar_10.7b_3.0
|
18 |
+
- model: freewheelin/free-solar-evo-v0.11
|
19 |
+
merge_method: model_stock
|
20 |
+
base_model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
|
21 |
+
dtype: bfloat16
|
22 |
+
```
|
23 |
+
|
24 |
+
## 💻 Usage
|
25 |
+
|
26 |
+
```python
|
27 |
+
!pip install -qU transformers accelerate
|
28 |
+
|
29 |
+
from transformers import AutoTokenizer
|
30 |
+
import transformers
|
31 |
+
import torch
|
32 |
+
|
33 |
+
model = "dazare/chimera-ggobugi-solar-v1"
|
34 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
35 |
+
|
36 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
37 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
38 |
+
pipeline = transformers.pipeline(
|
39 |
+
"text-generation",
|
40 |
+
model=model,
|
41 |
+
torch_dtype=torch.float16,
|
42 |
+
device_map="auto",
|
43 |
+
)
|
44 |
+
|
45 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
46 |
+
print(outputs[0]["generated_text"])
|
47 |
+
```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "chihoonlee10/T3Q-ko-solar-dpo-v7.0",
|
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": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 14336,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 48,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 2,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.42.3",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
|
4 |
+
- model: MoaData/Myrrh_solar_10.7b_3.0
|
5 |
+
- model: freewheelin/free-solar-evo-v0.11
|
6 |
+
merge_method: model_stock
|
7 |
+
base_model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
|
8 |
+
dtype: bfloat16
|
model-00001-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adbf4564e9ef987c2f23a41b382ba2028bc0a15116f6ae34ba6f715140e112ac
|
3 |
+
size 960521552
|
model-00002-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f8a5b9b925384c88a31c3eff74272bf2d881187301bf1c97508feef54097a15
|
3 |
+
size 989890720
|
model-00003-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e395985e57aab59ebc190783de6cb0d005d43733f70b63c860539fff1040cecc
|
3 |
+
size 989890728
|
model-00004-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f52bfd96241c4faac8e0f488f2f0b1db85638411d8730461c92abc23abd8497
|
3 |
+
size 998287760
|
model-00005-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd9c19d47e8bc710524d42af3d0ff0fef4affa8c88e6a5f0eeb9c337106a40f5
|
3 |
+
size 947956216
|
model-00006-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7a021561a23750974c2effd2e80f1e3a00d49daef7387c6cae72d2d8d739baa
|
3 |
+
size 989890728
|
model-00007-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca583da0bcdaa5e1257452332205b4fb2f681e0eaa3306f5e4bba5c66908823a
|
3 |
+
size 989890720
|
model-00008-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de484bc10cc42d741cf47f1cd94ca481f1e1e0a32c64cbb776be7478e6d011d
|
3 |
+
size 998287760
|
model-00009-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32db8f34d3736c204ff1c52cd2ffc2ce95e0e4292e9c23582931d498660d009f
|
3 |
+
size 947956216
|
model-00010-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d31d95041297a85c381b244eed8fe0e625e9a24cad7fe45c103133edd9bc6565
|
3 |
+
size 989890728
|
model-00011-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f0f205e4f6cbe74413bdd7c033ec1b0e7e0be2aec9bd9714d203bb3883f621
|
3 |
+
size 989890728
|
model-00012-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f3c02b0b25f5fb2912aa3f18153aedf9d6882ce87a2edd04aced1af6efa3595
|
3 |
+
size 998287752
|
model-00013-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7961c1f46cbbe2382d0064555fe8bbbf5a924e302708572dbb8cd032ae53c472
|
3 |
+
size 947956216
|
model-00014-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb3a7c7ded85b2aaf7575d4ef8aca69532830f2bac49069d554e4fd130ab58ea
|
3 |
+
size 989890728
|
model-00015-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95e048d7f699c72e54b4ce22b2dd3670f723087cbcb024313168b8c0f1a9a86a
|
3 |
+
size 989890728
|
model-00016-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a16da1111b59f1bc78f2bf3cbdb62efc72d620eedd172d590301d425e9ddb668
|
3 |
+
size 998287752
|
model-00017-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31988e50f167a306087a7c603a8f261e27c87fe35b04ec76e406be7c8dd019a3
|
3 |
+
size 947956216
|
model-00018-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a55f13ae08db1f62d8baf661d7b63177c541aaa42e66a28d115dcd860e9058dc
|
3 |
+
size 989890728
|
model-00019-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6bf0005321ade484db79b33e7e8b3aa798f9f7197fd69b21ed9ad68e8c57405
|
3 |
+
size 989890728
|
model-00020-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce4163a1096f542e7d5e8b9bc25ac1147558f65fa775e2962ad932e43a3eb8aa
|
3 |
+
size 998287752
|
model-00021-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d5d487cc51226463db71997b0c6c029ee0d956576885c011e4bcedbebc155a6
|
3 |
+
size 947956192
|
model-00022-of-00022.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b735783c04175b5426175089fd4c787288db5ee661d2ffcab4e3c42b5c6268e0
|
3 |
+
size 872450064
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 21463048192}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"padding_side": "left",
|
39 |
+
"sp_model_kwargs": {},
|
40 |
+
"spaces_between_special_tokens": false,
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": true
|
45 |
+
}
|