Upload README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,13 @@ license: other
|
|
5 |
model_creator: CodeFuse AI
|
6 |
model_name: CodeFuse CodeLlama 34B
|
7 |
model_type: llama
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
quantized_by: TheBloke
|
9 |
tasks:
|
10 |
- code-generation
|
@@ -42,6 +49,7 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
|
|
42 |
<!-- repositories-available start -->
|
43 |
## Repositories available
|
44 |
|
|
|
45 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeFuse-CodeLlama-34B-GPTQ)
|
46 |
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeFuse-CodeLlama-34B-GGUF)
|
47 |
* [CodeFuse AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B)
|
@@ -274,6 +282,17 @@ The context length of finetuning is 4K while it is able to be finetuned by 16k c
|
|
274 |
|
275 |
<br>
|
276 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
277 |
## Performance
|
278 |
|
279 |
|
@@ -393,6 +412,16 @@ CodeFuse-CodeLlama34B-MFT 是一个通过QLoRA对基座模型CodeLlama-34b-Pytho
|
|
393 |
|
394 |
<br>
|
395 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
396 |
## 评测表现(代码)
|
397 |
|
398 |
| 模型 | HumanEval(pass@1) | 日期 |
|
|
|
5 |
model_creator: CodeFuse AI
|
6 |
model_name: CodeFuse CodeLlama 34B
|
7 |
model_type: llama
|
8 |
+
prompt_template: '<|role_start|>system<|role_end|>{system_message}
|
9 |
+
|
10 |
+
<|role_start|>human<|role_end|>{prompt}
|
11 |
+
|
12 |
+
<|role_start|>bot<|role_end|>
|
13 |
+
|
14 |
+
'
|
15 |
quantized_by: TheBloke
|
16 |
tasks:
|
17 |
- code-generation
|
|
|
49 |
<!-- repositories-available start -->
|
50 |
## Repositories available
|
51 |
|
52 |
+
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/CodeFuse-CodeLlama-34B-AWQ)
|
53 |
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/CodeFuse-CodeLlama-34B-GPTQ)
|
54 |
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/CodeFuse-CodeLlama-34B-GGUF)
|
55 |
* [CodeFuse AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/codefuse-ai/CodeFuse-CodeLlama-34B)
|
|
|
282 |
|
283 |
<br>
|
284 |
|
285 |
+
## Code Community
|
286 |
+
|
287 |
+
**Homepage**: 🏡 https://github.com/codefuse-ai (**Please give us your support with a Star🌟 + Fork🚀 + Watch👀**)
|
288 |
+
|
289 |
+
+ If you wish to fine-tune the model yourself, you can visit ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
|
290 |
+
|
291 |
+
+ If you wish to deploy the model yourself, you can visit ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
|
292 |
+
|
293 |
+
+ If you wish to see a demo of the model, you can visit ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
|
294 |
+
|
295 |
+
|
296 |
## Performance
|
297 |
|
298 |
|
|
|
412 |
|
413 |
<br>
|
414 |
|
415 |
+
## 代码社区
|
416 |
+
**大本营**: 🏡 https://github.com/codefuse-ai (**欢迎为我们的项目一键三连 Star🌟 + Fork🚀 + Watch👀**)
|
417 |
+
|
418 |
+
+ 如果您想自己微调该模型,可以访问 ✨[MFTCoder](https://github.com/codefuse-ai/MFTCoder)✨✨
|
419 |
+
|
420 |
+
+ 如果您想自己部署该模型,可以访问 ✨[FasterTransformer4CodeFuse](https://github.com/codefuse-ai/FasterTransformer4CodeFuse)✨✨
|
421 |
+
|
422 |
+
+ 如果您想观看该模型示例,可以访问 ✨[CodeFuse Demo](https://github.com/codefuse-ai/codefuse)✨✨
|
423 |
+
|
424 |
+
|
425 |
## 评测表现(代码)
|
426 |
|
427 |
| 模型 | HumanEval(pass@1) | 日期 |
|