LoneStriker
commited on
Commit
•
68195fb
1
Parent(s):
2807922
Upload folder using huggingface_hub
Browse files- README.md +61 -0
- config.json +27 -0
- generation_config.json +6 -0
- output-00001-of-00005.safetensors +3 -0
- output-00002-of-00005.safetensors +3 -0
- output-00003-of-00005.safetensors +3 -0
- output-00004-of-00005.safetensors +3 -0
- output-00005-of-00005.safetensors +3 -0
- pytorch_model.bin.index.json +865 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +134 -0
README.md
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: deepseek
|
4 |
+
license_link: LICENSE
|
5 |
+
datasets:
|
6 |
+
- unalignment/spicy-3.1
|
7 |
+
---
|
8 |
+
|
9 |
+
<p align="center">
|
10 |
+
<img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
|
11 |
+
</p>
|
12 |
+
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
|
13 |
+
<hr>
|
14 |
+
|
15 |
+
# Fine-tune of Deepseek 67B
|
16 |
+
|
17 |
+
Fine-tuned with jondurbin's unalignment/spicy-3.1 for 1 epoch.
|
18 |
+
|
19 |
+
|
20 |
+
### 1. Introduction of Deepseek LLM
|
21 |
+
|
22 |
+
Introducing DeepSeek LLM, an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. In order to foster research, we have made DeepSeek LLM 7B/67B Base and DeepSeek LLM 7B/67B Chat open source for the research community.
|
23 |
+
|
24 |
+
|
25 |
+
### 2. Model Summary
|
26 |
+
`deepseek-llm-67b-base` is a 67B parameter model with Grouped-Query Attention trained on 2 trillion tokens from scratch.
|
27 |
+
- **Home Page:** [DeepSeek](https://deepseek.com/)
|
28 |
+
- **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
|
29 |
+
- **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)
|
30 |
+
|
31 |
+
|
32 |
+
### 3. How to Use
|
33 |
+
Here give some examples of how to use our model.
|
34 |
+
#### Text Completion
|
35 |
+
```python
|
36 |
+
import torch
|
37 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
|
38 |
+
|
39 |
+
model_name = "deepseek-ai/deepseek-llm-67b-base"
|
40 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
41 |
+
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
|
42 |
+
model.generation_config = GenerationConfig.from_pretrained(model_name)
|
43 |
+
model.generation_config.pad_token_id = model.generation_config.eos_token_id
|
44 |
+
|
45 |
+
text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
|
46 |
+
inputs = tokenizer(text, return_tensors="pt")
|
47 |
+
outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
|
48 |
+
|
49 |
+
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
50 |
+
print(result)
|
51 |
+
```
|
52 |
+
|
53 |
+
### 4. License
|
54 |
+
This code repository is licensed under the MIT License. The use of DeepSeek LLM models is subject to the Model License. DeepSeek LLM supports commercial use.
|
55 |
+
|
56 |
+
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL) for more details.
|
57 |
+
|
58 |
+
### 5. Contact
|
59 |
+
|
60 |
+
If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
|
61 |
+
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/aiml/models/deepseek-llm-67b-base",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 22016,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 64,
|
16 |
+
"num_hidden_layers": 95,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.34.1",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 102400
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100000,
|
4 |
+
"eos_token_id": 100001,
|
5 |
+
"transformers_version": "4.34.1"
|
6 |
+
}
|
output-00001-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8447b5ee4a21f8dbc8f2f5b21af70b847e3b5976ec6cded9481704abce984141
|
3 |
+
size 8521544864
|
output-00002-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:135c2d24ea4eb13ce03e838e44c01b2b458089eeb3b81aba3b5bc5292f67129d
|
3 |
+
size 8512123928
|
output-00003-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c87b12d6dad70fa95382e2b2af9e8314f24228488136a8d36084aeeaa8c2abf
|
3 |
+
size 8494892648
|
output-00004-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e735015b43b10e95feb334f12ca5875ebbd44ac3ab6bef48fc6ec3cff7b95262
|
3 |
+
size 8586575144
|
output-00005-of-00005.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca5b6ecdaeaec1a4497393d420c2df54ecc38737d384f7e61495998d7688f781
|
3 |
+
size 6483446288
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,865 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 134850002944
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00014-of-00014.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
|
253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
|
254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
|
255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
|
256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
|
266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
|
267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
|
268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
|
269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
323 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
324 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
|
325 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
|
326 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
|
327 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
|
328 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
329 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
330 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
331 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
332 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
333 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
334 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
335 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
336 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
337 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
|
338 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
|
339 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
|
340 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
|
341 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
342 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
343 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
344 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
345 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
346 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
347 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
348 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
349 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
350 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
351 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
352 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
353 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
354 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
355 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
356 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
357 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
358 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
359 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
360 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
361 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
362 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
363 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
364 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
365 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
366 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
367 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
368 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
369 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
370 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
371 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
372 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
373 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
374 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
375 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
376 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
377 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
378 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
379 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
380 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
381 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
382 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
383 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
384 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
385 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
386 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
387 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
|
388 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
|
389 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
|
390 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
|
391 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
392 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
393 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
394 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
395 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
396 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
397 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
398 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
399 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
400 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
|
401 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
|
402 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
|
403 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
|
404 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
405 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
406 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
407 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
408 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
409 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
410 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
411 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
412 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
413 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
414 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
|
415 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
|
416 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
|
417 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
|
418 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
|
419 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
|
420 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
|
421 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
|
422 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
423 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
424 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
425 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
426 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
427 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
428 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
429 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
430 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
431 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
432 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
433 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
434 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
435 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
436 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
437 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
438 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
439 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
440 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
441 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
442 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
443 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
444 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
445 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
446 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
447 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
448 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
449 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
450 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
451 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
452 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
453 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
454 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
455 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
456 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
457 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
458 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
459 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
|
460 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
|
461 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
|
462 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
|
463 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
464 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
465 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
466 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
467 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
468 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
469 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
470 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
471 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
472 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
|
473 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
|
474 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
|
475 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
|
476 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
477 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
478 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
479 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
480 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
481 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
482 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
483 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
484 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
485 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
486 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
487 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
488 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
489 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
490 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
491 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
492 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
493 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
494 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
495 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
496 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
497 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
498 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
499 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
500 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
501 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
502 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
503 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
504 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
505 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
506 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
507 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
508 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
509 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
510 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
511 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
512 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
513 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
514 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
515 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
516 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
517 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
518 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
519 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
520 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
521 |
+
"model.layers.60.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
522 |
+
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
523 |
+
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
524 |
+
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
525 |
+
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
526 |
+
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
527 |
+
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
528 |
+
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
529 |
+
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
530 |
+
"model.layers.61.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
531 |
+
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
|
532 |
+
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
|
533 |
+
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
|
534 |
+
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
|
535 |
+
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
536 |
+
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
537 |
+
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
538 |
+
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
539 |
+
"model.layers.62.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
540 |
+
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
541 |
+
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
542 |
+
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
543 |
+
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
544 |
+
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
|
545 |
+
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
|
546 |
+
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
|
547 |
+
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
|
548 |
+
"model.layers.63.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
549 |
+
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
550 |
+
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
551 |
+
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
552 |
+
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
553 |
+
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
554 |
+
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
555 |
+
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
556 |
+
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
557 |
+
"model.layers.64.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
558 |
+
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
559 |
+
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
560 |
+
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
561 |
+
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
562 |
+
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
563 |
+
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
564 |
+
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
565 |
+
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
566 |
+
"model.layers.65.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
567 |
+
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
568 |
+
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
569 |
+
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
570 |
+
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
571 |
+
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
572 |
+
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
573 |
+
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
574 |
+
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
575 |
+
"model.layers.66.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
576 |
+
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
577 |
+
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
578 |
+
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
579 |
+
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
580 |
+
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
581 |
+
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
582 |
+
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
583 |
+
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
584 |
+
"model.layers.67.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
585 |
+
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
586 |
+
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
587 |
+
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
588 |
+
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
589 |
+
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
590 |
+
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
591 |
+
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
592 |
+
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
593 |
+
"model.layers.68.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
594 |
+
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
|
595 |
+
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
|
596 |
+
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
|
597 |
+
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
|
598 |
+
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
599 |
+
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
600 |
+
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
601 |
+
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
602 |
+
"model.layers.69.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
603 |
+
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
604 |
+
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
605 |
+
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
606 |
+
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
607 |
+
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
|
608 |
+
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
|
609 |
+
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
|
610 |
+
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
|
611 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
612 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
613 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
614 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
615 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
616 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
617 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
618 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
619 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
620 |
+
"model.layers.70.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
621 |
+
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
622 |
+
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
623 |
+
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
624 |
+
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
625 |
+
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
626 |
+
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
627 |
+
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
628 |
+
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
629 |
+
"model.layers.71.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
630 |
+
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
631 |
+
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
632 |
+
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
633 |
+
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
634 |
+
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
635 |
+
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
636 |
+
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
637 |
+
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
638 |
+
"model.layers.72.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
639 |
+
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
640 |
+
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
641 |
+
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
642 |
+
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
643 |
+
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
644 |
+
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
645 |
+
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
646 |
+
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
647 |
+
"model.layers.73.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
648 |
+
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
649 |
+
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
650 |
+
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
651 |
+
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
652 |
+
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
653 |
+
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
654 |
+
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
655 |
+
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
656 |
+
"model.layers.74.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
657 |
+
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
658 |
+
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
659 |
+
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
660 |
+
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
661 |
+
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
662 |
+
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
663 |
+
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
664 |
+
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
665 |
+
"model.layers.75.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
666 |
+
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
|
667 |
+
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
|
668 |
+
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
|
669 |
+
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
|
670 |
+
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
671 |
+
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
672 |
+
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
673 |
+
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
674 |
+
"model.layers.76.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
675 |
+
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
676 |
+
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
677 |
+
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
678 |
+
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
679 |
+
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
|
680 |
+
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
|
681 |
+
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
|
682 |
+
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
|
683 |
+
"model.layers.77.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
684 |
+
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
685 |
+
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
686 |
+
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
687 |
+
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
688 |
+
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
689 |
+
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
690 |
+
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
691 |
+
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
692 |
+
"model.layers.78.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
693 |
+
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
694 |
+
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
695 |
+
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
696 |
+
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
697 |
+
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
698 |
+
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
699 |
+
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
700 |
+
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
701 |
+
"model.layers.79.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
702 |
+
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
703 |
+
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
704 |
+
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
705 |
+
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
706 |
+
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
707 |
+
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
708 |
+
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
709 |
+
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
710 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
711 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
712 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
713 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
714 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
715 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
716 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
717 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
718 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
719 |
+
"model.layers.80.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
720 |
+
"model.layers.80.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
721 |
+
"model.layers.80.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
722 |
+
"model.layers.80.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
723 |
+
"model.layers.80.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
724 |
+
"model.layers.80.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
725 |
+
"model.layers.80.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
726 |
+
"model.layers.80.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
727 |
+
"model.layers.80.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
728 |
+
"model.layers.81.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
729 |
+
"model.layers.81.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
730 |
+
"model.layers.81.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
731 |
+
"model.layers.81.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
732 |
+
"model.layers.81.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
733 |
+
"model.layers.81.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
734 |
+
"model.layers.81.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
735 |
+
"model.layers.81.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
736 |
+
"model.layers.81.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
737 |
+
"model.layers.82.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
738 |
+
"model.layers.82.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
|
739 |
+
"model.layers.82.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
|
740 |
+
"model.layers.82.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
|
741 |
+
"model.layers.82.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
|
742 |
+
"model.layers.82.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
743 |
+
"model.layers.82.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
744 |
+
"model.layers.82.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
745 |
+
"model.layers.82.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
746 |
+
"model.layers.83.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
747 |
+
"model.layers.83.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
748 |
+
"model.layers.83.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
749 |
+
"model.layers.83.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
750 |
+
"model.layers.83.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
751 |
+
"model.layers.83.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
|
752 |
+
"model.layers.83.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
|
753 |
+
"model.layers.83.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
|
754 |
+
"model.layers.83.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
|
755 |
+
"model.layers.84.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
756 |
+
"model.layers.84.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
757 |
+
"model.layers.84.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
758 |
+
"model.layers.84.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
759 |
+
"model.layers.84.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
760 |
+
"model.layers.84.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
761 |
+
"model.layers.84.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
762 |
+
"model.layers.84.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
763 |
+
"model.layers.84.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
764 |
+
"model.layers.85.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
765 |
+
"model.layers.85.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
766 |
+
"model.layers.85.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
767 |
+
"model.layers.85.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
768 |
+
"model.layers.85.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
769 |
+
"model.layers.85.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
770 |
+
"model.layers.85.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
771 |
+
"model.layers.85.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
772 |
+
"model.layers.85.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
773 |
+
"model.layers.86.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
774 |
+
"model.layers.86.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
775 |
+
"model.layers.86.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
776 |
+
"model.layers.86.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
777 |
+
"model.layers.86.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
778 |
+
"model.layers.86.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
779 |
+
"model.layers.86.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
780 |
+
"model.layers.86.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
781 |
+
"model.layers.86.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
782 |
+
"model.layers.87.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
783 |
+
"model.layers.87.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
784 |
+
"model.layers.87.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
785 |
+
"model.layers.87.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
786 |
+
"model.layers.87.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
787 |
+
"model.layers.87.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
788 |
+
"model.layers.87.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
789 |
+
"model.layers.87.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
790 |
+
"model.layers.87.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
791 |
+
"model.layers.88.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
792 |
+
"model.layers.88.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
793 |
+
"model.layers.88.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
794 |
+
"model.layers.88.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
795 |
+
"model.layers.88.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
796 |
+
"model.layers.88.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
797 |
+
"model.layers.88.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
798 |
+
"model.layers.88.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
799 |
+
"model.layers.88.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
800 |
+
"model.layers.89.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
801 |
+
"model.layers.89.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
|
802 |
+
"model.layers.89.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
|
803 |
+
"model.layers.89.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
|
804 |
+
"model.layers.89.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
|
805 |
+
"model.layers.89.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
806 |
+
"model.layers.89.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
807 |
+
"model.layers.89.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
808 |
+
"model.layers.89.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
809 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
810 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
|
811 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
|
812 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
|
813 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
|
814 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
|
815 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
|
816 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
|
817 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
|
818 |
+
"model.layers.90.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
819 |
+
"model.layers.90.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
820 |
+
"model.layers.90.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
821 |
+
"model.layers.90.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
822 |
+
"model.layers.90.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
823 |
+
"model.layers.90.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
|
824 |
+
"model.layers.90.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
|
825 |
+
"model.layers.90.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
|
826 |
+
"model.layers.90.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
|
827 |
+
"model.layers.91.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
828 |
+
"model.layers.91.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
829 |
+
"model.layers.91.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
830 |
+
"model.layers.91.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
831 |
+
"model.layers.91.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
832 |
+
"model.layers.91.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
|
833 |
+
"model.layers.91.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
|
834 |
+
"model.layers.91.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
|
835 |
+
"model.layers.91.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
|
836 |
+
"model.layers.92.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
837 |
+
"model.layers.92.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
838 |
+
"model.layers.92.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
839 |
+
"model.layers.92.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
840 |
+
"model.layers.92.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
841 |
+
"model.layers.92.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
|
842 |
+
"model.layers.92.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
|
843 |
+
"model.layers.92.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
|
844 |
+
"model.layers.92.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
|
845 |
+
"model.layers.93.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
846 |
+
"model.layers.93.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
847 |
+
"model.layers.93.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
848 |
+
"model.layers.93.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
849 |
+
"model.layers.93.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
850 |
+
"model.layers.93.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
|
851 |
+
"model.layers.93.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
|
852 |
+
"model.layers.93.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
|
853 |
+
"model.layers.93.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
|
854 |
+
"model.layers.94.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
855 |
+
"model.layers.94.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
|
856 |
+
"model.layers.94.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
|
857 |
+
"model.layers.94.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
|
858 |
+
"model.layers.94.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
|
859 |
+
"model.layers.94.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
|
860 |
+
"model.layers.94.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
|
861 |
+
"model.layers.94.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
|
862 |
+
"model.layers.94.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
|
863 |
+
"model.norm.weight": "pytorch_model-00014-of-00014.bin"
|
864 |
+
}
|
865 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"100000": {
|
4 |
+
"content": "<|begin▁of▁sentence|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100001": {
|
12 |
+
"content": "<|end▁of▁sentence|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"100002": {
|
20 |
+
"content": "ø",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": false
|
26 |
+
},
|
27 |
+
"100003": {
|
28 |
+
"content": "ö",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
+
},
|
35 |
+
"100004": {
|
36 |
+
"content": "ú",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": false
|
42 |
+
},
|
43 |
+
"100005": {
|
44 |
+
"content": "ÿ",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"100006": {
|
52 |
+
"content": "õ",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"100007": {
|
60 |
+
"content": "÷",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"100008": {
|
68 |
+
"content": "û",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"100009": {
|
76 |
+
"content": "ý",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"100010": {
|
84 |
+
"content": "À",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"100011": {
|
92 |
+
"content": "ù",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"100012": {
|
100 |
+
"content": "Á",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
},
|
107 |
+
"100013": {
|
108 |
+
"content": "þ",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": true,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": false
|
114 |
+
},
|
115 |
+
"100014": {
|
116 |
+
"content": "ü",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": true,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": false
|
122 |
+
}
|
123 |
+
},
|
124 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
125 |
+
"clean_up_tokenization_spaces": false,
|
126 |
+
"eos_token": "<|end▁of▁sentence|>",
|
127 |
+
"legacy": true,
|
128 |
+
"model_max_length": 4096,
|
129 |
+
"pad_token": "<|end▁of▁sentence|>",
|
130 |
+
"sp_model_kwargs": {},
|
131 |
+
"tokenizer_class": "LlamaTokenizer",
|
132 |
+
"unk_token": null,
|
133 |
+
"use_default_system_prompt": true
|
134 |
+
}
|