Abdulhanan2006
commited on
Commit
•
1a25d55
1
Parent(s):
f73926f
Upload folder using huggingface_hub
Browse files- README.md +63 -0
- config.json +29 -0
- mergekit_config.yml +17 -0
- model-00001-of-00028.safetensors +3 -0
- model-00002-of-00028.safetensors +3 -0
- model-00003-of-00028.safetensors +3 -0
- model-00004-of-00028.safetensors +3 -0
- model-00005-of-00028.safetensors +3 -0
- model-00006-of-00028.safetensors +3 -0
- model-00007-of-00028.safetensors +3 -0
- model-00008-of-00028.safetensors +3 -0
- model-00009-of-00028.safetensors +3 -0
- model-00010-of-00028.safetensors +3 -0
- model-00011-of-00028.safetensors +3 -0
- model-00012-of-00028.safetensors +3 -0
- model-00013-of-00028.safetensors +3 -0
- model-00014-of-00028.safetensors +3 -0
- model-00015-of-00028.safetensors +3 -0
- model-00016-of-00028.safetensors +3 -0
- model-00017-of-00028.safetensors +3 -0
- model-00018-of-00028.safetensors +3 -0
- model-00019-of-00028.safetensors +3 -0
- model-00020-of-00028.safetensors +3 -0
- model-00021-of-00028.safetensors +3 -0
- model-00022-of-00028.safetensors +3 -0
- model-00023-of-00028.safetensors +3 -0
- model-00024-of-00028.safetensors +3 -0
- model-00025-of-00028.safetensors +3 -0
- model-00026-of-00028.safetensors +3 -0
- model-00027-of-00028.safetensors +3 -0
- model-00028-of-00028.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- PygmalionAI/pygmalion-2-13b
|
7 |
+
- Abdulhanan2006/LogicLumina-L3-13B
|
8 |
+
base_model:
|
9 |
+
- PygmalionAI/pygmalion-2-13b
|
10 |
+
- Abdulhanan2006/LogicLumina-L3-13B
|
11 |
+
---
|
12 |
+
|
13 |
+
# LogicLumina-L3-13B-v2
|
14 |
+
|
15 |
+
LogicLumina-L3-13B-v2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [PygmalionAI/pygmalion-2-13b](https://huggingface.co/PygmalionAI/pygmalion-2-13b)
|
17 |
+
* [Abdulhanan2006/LogicLumina-L3-13B](https://huggingface.co/Abdulhanan2006/LogicLumina-L3-13B)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: PygmalionAI/pygmalion-2-13b
|
25 |
+
layer_range: [0, 40]
|
26 |
+
- model: Abdulhanan2006/LogicLumina-L3-13B
|
27 |
+
layer_range: [0, 40]
|
28 |
+
merge_method: slerp
|
29 |
+
base_model: PygmalionAI/pygmalion-2-13b
|
30 |
+
parameters:
|
31 |
+
t:
|
32 |
+
- filter: self_attn
|
33 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
+
- filter: mlp
|
35 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
+
- value: 0.4
|
37 |
+
dtype: bfloat16
|
38 |
+
```
|
39 |
+
|
40 |
+
## 💻 Usage
|
41 |
+
|
42 |
+
```python
|
43 |
+
!pip install -qU transformers accelerate
|
44 |
+
|
45 |
+
from transformers import AutoTokenizer
|
46 |
+
import transformers
|
47 |
+
import torch
|
48 |
+
|
49 |
+
model = "Abdulhanan2006/LogicLumina-L3-13B-v2"
|
50 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
51 |
+
|
52 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
53 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
54 |
+
pipeline = transformers.pipeline(
|
55 |
+
"text-generation",
|
56 |
+
model=model,
|
57 |
+
torch_dtype=torch.float16,
|
58 |
+
device_map="auto",
|
59 |
+
)
|
60 |
+
|
61 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
62 |
+
print(outputs[0]["generated_text"])
|
63 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "PygmalionAI/pygmalion-2-13b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]",
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 13824,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 40,
|
18 |
+
"num_hidden_layers": 40,
|
19 |
+
"num_key_value_heads": 40,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 10000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.39.3",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 32000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: PygmalionAI/pygmalion-2-13b
|
5 |
+
layer_range: [0, 40]
|
6 |
+
- model: Abdulhanan2006/LogicLumina-L3-13B
|
7 |
+
layer_range: [0, 40]
|
8 |
+
merge_method: slerp
|
9 |
+
base_model: PygmalionAI/pygmalion-2-13b
|
10 |
+
parameters:
|
11 |
+
t:
|
12 |
+
- filter: self_attn
|
13 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
+
- filter: mlp
|
15 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
+
- value: 0.4
|
17 |
+
dtype: bfloat16
|
model-00001-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e855f40a57be380f71baccbb16054c93673152c1ef423156c87ed86cbd785d2
|
3 |
+
size 938486328
|
model-00002-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb3c412d64126aab65106791dc075c6e7b375d84752176eb6c92641060878812
|
3 |
+
size 985704256
|
model-00003-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d8a8253bfe58e7c1ae8e60ae9253266316987632126e7b1229893fa423028a7
|
3 |
+
size 917525776
|
model-00004-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57b839048fcd1545bc0f8785465d42a33e15113a86217b2af03b95bfb3957419
|
3 |
+
size 985704272
|
model-00005-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d58c312afb4a250259921ef6d89bde64864ef3e746b0fcf3a62d7ac4801234b
|
3 |
+
size 917525776
|
model-00006-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f8187403858cd3ab2912122d06253d8d3c7e5ee7451cfa6ab2f83b04c29018c
|
3 |
+
size 985704272
|
model-00007-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02ad5cc4d28edaa0288e498e893252e947988086268f11d51b2fd63b5f3b8e54
|
3 |
+
size 917525776
|
model-00008-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba65a88a281a299a469ae7fd20ddc1518b328496d096b9d5049a0bee64eb4aa
|
3 |
+
size 985704272
|
model-00009-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c3f4a005773d22218358f0658f77f671c5035ac7f518090fec1570b3ded0d7
|
3 |
+
size 917525776
|
model-00010-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e73e51b61252f73c52d219f5524b015361b1ea674c1cb6fbcaf0bbedff942c4
|
3 |
+
size 985704264
|
model-00011-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af7e3d90c91b0aba76fbb2633821da1a8cba454bfa8489ad032c4c62581b3171
|
3 |
+
size 917525776
|
model-00012-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c99a99dfa6d22eac78d338af431a03e9a43fbbe2e641eca4d32b0c84e6ae3de
|
3 |
+
size 985704272
|
model-00013-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bea24ab734760d7b21bce00d513fc83f8127ecc7521fc7dfede80f6f0df4f707
|
3 |
+
size 917525776
|
model-00014-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24475c682afcabfa2df7788837bd9c0e5b6b2269acf86c40e8b2c71628e48a77
|
3 |
+
size 985704272
|
model-00015-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fce769e91caa22003cb0b71edab419b077c4a4aef954091180a64bb8d87bccb
|
3 |
+
size 917525776
|
model-00016-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1427a5a492aa1125be99797bd5550a49766661948ef865e2b227796db056c988
|
3 |
+
size 985704272
|
model-00017-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04d3f04be54250cbc2e60d4c147594abc653682276eff3a78138cecbc81d0749
|
3 |
+
size 917525768
|
model-00018-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa69b36f4b6a7077b185ef7960f2294a3dadea7b51a704dfa4795fedbb7fc147
|
3 |
+
size 985704272
|
model-00019-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d053cf59496a2649a75f9cfd4f160c4bdd4ee7d9087d6a7a02a37d43b3855189
|
3 |
+
size 917525776
|
model-00020-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3f2b1b57c35a09b2cc45e2a168adb9eefa1de91226aedff6a44e69c2bdf4eb7
|
3 |
+
size 985704272
|
model-00021-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b7287858e50583615e90b2c37c8d8de1d32be09d1e587350ff1a6cc55a5202a
|
3 |
+
size 917525776
|
model-00022-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39cce7448daaea4bb118e9a73b07b67772f72985d818a5ca3353bb9e464d6349
|
3 |
+
size 985704272
|
model-00023-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91f07db85f96d5e27af5237d3afc09a49268963e5abcdb07eb075901e52ce5d8
|
3 |
+
size 917525776
|
model-00024-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a63de503984cb5434f8b3c45e905c2ae7f821748cbf9a4f716e55089cb07e6f8
|
3 |
+
size 985704264
|
model-00025-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c27a1741adf66e5c0979026e8de825e5ace9488bafdc9137587ad2ce32f62d7f
|
3 |
+
size 917525768
|
model-00026-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71bca143856f2803f1e1f3496e86c149397a961b7ea373a4b8fef42cbff7d3e7
|
3 |
+
size 985704256
|
model-00027-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3086572c0a50da0ab23f21d266a31850d198c24d4f6e3736651c30b9eccc4dfe
|
3 |
+
size 917525768
|
model-00028-of-00028.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1893bf93594d6154f87708463f0c1e1a99ec9cad5fccc795307dee4d2b2fde99
|
3 |
+
size 351294256
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 26031728640}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.35.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.38.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"trust_remote_code": false,
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": true,
|
43 |
+
"use_fast": true
|
44 |
+
}
|