Quantized models
Browse files- .gitattributes +6 -0
- LICENSE +0 -0
- Modelfile +2 -0
- README.md +48 -0
- deepseek-coder-7b-base-v1.5.f16.gguf +3 -0
- deepseek-coder-7b-base-v1.5.q4_0.gguf +3 -0
- deepseek-coder-7b-base-v1.5.q4_k.gguf +3 -0
- deepseek-coder-7b-base-v1.5.q5_k.gguf +3 -0
- deepseek-coder-7b-base-v1.5.q6_k.gguf +3 -0
- deepseek-coder-7b-base-v1.5.q8_0.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,9 @@ 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-coder-7b-base-v1.5.f16.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
deepseek-coder-7b-base-v1.5.q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
deepseek-coder-7b-base-v1.5.q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
deepseek-coder-7b-base-v1.5.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
deepseek-coder-7b-base-v1.5.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
deepseek-coder-7b-base-v1.5.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
LICENSE
ADDED
File without changes
|
Modelfile
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
FROM model.gguf
|
2 |
+
TEMPLATE """{{ .Prompt }}"""
|
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: deepseek-license
|
4 |
+
license_link: LICENSE
|
5 |
+
---
|
6 |
+
|
7 |
+
<p align="center">
|
8 |
+
<img width="1000px" alt="DeepSeek Coder" src="https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/pictures/logo.png?raw=true">
|
9 |
+
</p>
|
10 |
+
<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a> | <a href="https://coder.deepseek.com/">[🤖 Chat with DeepSeek Coder]</a> | <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a> | <a href="https://github.com/guoday/assert/blob/main/QR.png?raw=true">[Wechat(微信)]</a> </p>
|
11 |
+
<hr>
|
12 |
+
|
13 |
+
|
14 |
+
### 1. Introduction of Deepseek-Coder-7B-Base-v1.5
|
15 |
+
|
16 |
+
Deepseek-Coder-7B-Base-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective.
|
17 |
+
|
18 |
+
- **Home Page:** [DeepSeek](https://deepseek.com/)
|
19 |
+
- **Repository:** [deepseek-ai/deepseek-coder](https://github.com/deepseek-ai/deepseek-coder)
|
20 |
+
- **Chat With DeepSeek Coder:** [DeepSeek-Coder](https://coder.deepseek.com/)
|
21 |
+
|
22 |
+
|
23 |
+
### 2. Evaluation Results
|
24 |
+
<img width="1000px" alt="DeepSeek Coder" src="https://cdn-uploads.huggingface.co/production/uploads/6538815d1bdb3c40db94fbfa/xOtCTW5xdoLCKY4FR6tri.png">
|
25 |
+
|
26 |
+
|
27 |
+
|
28 |
+
### 3. How to Use
|
29 |
+
Here give an example of how to use our model.
|
30 |
+
```python
|
31 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
32 |
+
import torch
|
33 |
+
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-7b-base-v1.5", trust_remote_code=True)
|
34 |
+
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-7b-base-v1.5", trust_remote_code=True).cuda()
|
35 |
+
input_text = "#write a quick sort algorithm"
|
36 |
+
inputs = tokenizer(input_text, return_tensors="pt").cuda()
|
37 |
+
outputs = model.generate(**inputs, max_length=128)
|
38 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
39 |
+
```
|
40 |
+
|
41 |
+
### 4. License
|
42 |
+
This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use.
|
43 |
+
|
44 |
+
See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/LICENSE-MODEL) for more details.
|
45 |
+
|
46 |
+
### 5. Contact
|
47 |
+
|
48 |
+
If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
|
deepseek-coder-7b-base-v1.5.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7468c44f24a0219a58157a1d80165ce023e157be4832f2021b51fd2addbb053c
|
3 |
+
size 13825629440
|
deepseek-coder-7b-base-v1.5.q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70c5902e95a9f8a4df84a96c2de692dcff66962e676616374e82632a6842e24
|
3 |
+
size 4000472352
|
deepseek-coder-7b-base-v1.5.q4_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1cf0033f2089f91e1ec313a0daab9c1599b48016c42dbf1d9a419296bd1a4c2
|
3 |
+
size 4223769888
|
deepseek-coder-7b-base-v1.5.q5_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8413459ad72598c53cafd55102b6dc68e89b7ab5de2a9ae1cc1504e73aa81618
|
3 |
+
size 4926840096
|
deepseek-coder-7b-base-v1.5.q6_k.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4f1d480eaa600143498a588f5034792b1ea7794ae4dfb537c961aedf6599254
|
3 |
+
size 5673852192
|
deepseek-coder-7b-base-v1.5.q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fd1fb1e096b67c386111c782ea5f7100f120f14e1b14c77922930605f2dc288
|
3 |
+
size 7347395872
|