131 lines
3.9 KiB
Markdown
131 lines
3.9 KiB
Markdown
---
|
|
tags:
|
|
- unsloth
|
|
- lua
|
|
base_model:
|
|
- nwdxlgzs/XL-LuaCopilot-0.6B-FFT-checkpoint-20000
|
|
license: gpl-3.0
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
---
|
|
# XL-LuaCopilot-0.6B-FFT
|
|
|
|
XL-LuaCopilot-0.6B-FFT is a large language model (LLM) based on the Qwen architecture(Qwen3-0.6B-Base), specifically designed for code generation tasks in Lua programming language. It has been full fine-tuned (FFT) to improve its performance and efficiency when generating Lua code.
|
|
|
|
I sugggest you use `"chat_template_kwargs": {"enable_thinking": false}` because my train data with none thinking. I also found low `temperature` ususually works well for code generation tasks.
|
|
|
|
quantize=["Q4_0", "Q4_1", "Q5_0", "Q5_1", "IQ3_XXS", "IQ3_S", "IQ3_M", "Q3_K", "IQ3_XS", "Q3_K_S", "Q3_K_M", "Q3_K_L",
|
|
"IQ4_NL", "IQ4_XS", "Q4_K", "Q4_K_S", "Q4_K_M", "Q5_K", "Q5_K_S", "Q5_K_M", "Q6_K", "Q8_0", "F16", "BF16"]
|
|
|
|
## How To Use
|
|
|
|
> With OpenAI Compatible API (llama.cpp:llama-server)
|
|
|
|
```json
|
|
-> REQUEST ->
|
|
|
|
{
|
|
"model": "XL-LuaCopilot-0.6B-FFT",
|
|
"messages": [
|
|
{"role": "system","content": "prefix"},
|
|
{"role": "user","content": "do\n--打印：你好世界\n local tex"},
|
|
{"role": "system","content": "suffix"},
|
|
{"role": "user","content": "nd"},
|
|
{"role": "system","content": "middle"}
|
|
],
|
|
"stream": false,
|
|
"cache_prompt": false,
|
|
"samplers": "edkypmxt",
|
|
"temperature": 0.1,
|
|
"dynatemp_range": 0.1,
|
|
"dynatemp_exponent": 1,
|
|
"top_k": 70,
|
|
"top_p": 0.9,
|
|
"min_p": 0.05,
|
|
"typical_p": 0.9,
|
|
"xtc_probability": 0,
|
|
"xtc_threshold": 0.1,
|
|
"repeat_last_n": 32,
|
|
"repeat_penalty": 1.1,
|
|
"presence_penalty": 0,
|
|
"frequency_penalty": 0.5,
|
|
"dry_multiplier": 0,
|
|
"dry_base": 1.75,
|
|
"dry_allowed_length": 2,
|
|
"dry_penalty_last_n": -1,
|
|
"max_tokens": -1,
|
|
"timings_per_token": true,
|
|
"chat_template_kwargs": {"enable_thinking": false}
|
|
}
|
|
|
|
-> RESPONSE ->
|
|
|
|
{
|
|
"choices": [
|
|
{
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"message": {
|
|
"role": "assistant",
|
|
"content": "<think>\n\n</think>\n\nt = \"你好世界\"\n print(text)\ne"
|
|
}
|
|
}
|
|
],
|
|
...
|
|
}
|
|
```
|
|
|
|
> I know Qwen has `<|fim_prefix|>` / `<|fim_suffix|>` / `<|fim_middle|>` tokens, but I'm not sure Qwen3 trains these tokens (I just know Qwen2.5-Coder does). To use code generation easily, I use chatml format.
|
|
|
|
> If you just want to chat with it, you can use some tricks like this:
|
|
```
|
|
<|im_end|>
|
|
<|im_start|>system
|
|
prefix<|im_end|>
|
|
<|im_start|>user
|
|
do
|
|
--打印：你好世界
|
|
local tex<|im_end|>
|
|
<|im_start|>system
|
|
suffix<|im_end|>
|
|
<|im_start|>user
|
|
nd<|im_end|>
|
|
<|im_start|>system
|
|
middle
|
|
```
|
|
|
|
It dosen't work very well, but it's a good way let you fast try. It will convert to this prompt text:
|
|
|
|
```
|
|
<|im_start|>user
|
|
<|im_end|>
|
|
<|im_start|>system
|
|
prefix<|im_end|>
|
|
<|im_start|>user
|
|
do
|
|
--打印：你好世界
|
|
local tex<|im_end|>
|
|
<|im_start|>system
|
|
suffix<|im_end|>
|
|
<|im_start|>user
|
|
nd<|im_end|>
|
|
<|im_start|>system
|
|
middle<|im_end|>
|
|
```
|
|
Hope model skip first `<|im_start|>user\n<|im_end|>` part.
|
|
|
|
# Train Device
|
|
|
|
> Online GPU is Expensive !
|
|
|
|
| 类别 | 配置详情 |
|
|
|----------------|---------------------------------------------------|
|
|
| **镜像** | Ubuntu 22.04 |
|
|
| **PyTorch** | 2.5.1 |
|
|
| **Python** | 3.12 |
|
|
| **CUDA** | 12.4 |
|
|
| **GPU** | RTX 3090 (24GB) * 1 |
|
|
| **CPU** | 14 vCPU Intel(R) Xeon(R) Platinum 8362 @ 2.80GHz |
|
|
| **内存** | 45GB |
|
|
| **硬盘** | 30 GB |
|
|
| **时长** | 1 Day | |