LoneStriker
commited on
Commit
•
96a35f3
1
Parent(s):
3b3bf4e
Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +61 -0
- deepseek-llm-67b-Spicy-3.1-Q4_K_M.gguf +3 -0
- deepseek-llm-67b-Spicy-3.1-Q4_K_S.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
deepseek-llm-67b-Spicy-3.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
deepseek-llm-67b-Spicy-3.1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
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 [[email protected]](mailto:[email protected]).
|
61 |
+
|
deepseek-llm-67b-Spicy-3.1-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87806551b6e9ebf93bb71318c2e499d3a6a0d2b00323aa5d0510852c788010fb
|
3 |
+
size 40439274528
|
deepseek-llm-67b-Spicy-3.1-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:696b4e74ee269c7a2687b07b614643cd3c0ed9b51fbadd0ad20a409a535e3af8
|
3 |
+
size 38246603808
|