初始化项目,由ModelHub XC社区提供模型
Model: zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2 Source: Original Platform
This commit is contained in:
75
README.md
Normal file
75
README.md
Normal file
@@ -0,0 +1,75 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-0.6B-Base
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- qwen3
|
||||
- math
|
||||
- sft
|
||||
- qlora
|
||||
- merged-lora
|
||||
- fp16
|
||||
---
|
||||
|
||||
# qwen3-0.6b-math-l45-qlora-merged-fp16-v2
|
||||
|
||||
Merged fp16 model from `Qwen/Qwen3-0.6B-Base` plus a QLoRA SFT adapter trained for MATH level 4-5 problem solving.
|
||||
|
||||
This is the corrected SFT v2 run using the train split for training. Final 500-question evaluation is intentionally separate.
|
||||
|
||||
## Training Summary
|
||||
|
||||
- Base model: `Qwen/Qwen3-0.6B-Base`
|
||||
- Train file: `/kaggle/input/datasets/anurhalizah/math-he/math_level45_train.parquet`
|
||||
- Test file: `/kaggle/input/datasets/anurhalizah/math-he/math_level45_test.parquet`
|
||||
- Train rows used: `3994`
|
||||
- Train subset size: `3994`
|
||||
- Smoke loss eval rows: `200`
|
||||
- Max sequence length: `2048`
|
||||
- Epochs: `3`
|
||||
- Learning rate: `0.0002`
|
||||
- Precision: fp16
|
||||
- Merge method: `manual_lora_cpu`
|
||||
- Merged LoRA matrices: `196`
|
||||
|
||||
## Prompt Format
|
||||
|
||||
```text
|
||||
### System:
|
||||
{system_prompt}
|
||||
|
||||
### Problem:
|
||||
{problem}
|
||||
|
||||
### Solution:
|
||||
|
||||
```
|
||||
|
||||
System prompt:
|
||||
|
||||
```text
|
||||
You are a precise mathematical problem solver.
|
||||
Follow this exact output contract:
|
||||
1. Solve the problem step by step with concise reasoning.
|
||||
2. Use valid LaTeX math notation for mathematical expressions.
|
||||
3. Preserve LaTeX commands such as \frac{...}{...}, \sqrt{...}, x^{...}, subscripts, equations, and inequalities.
|
||||
4. Put the final answer on its own last line exactly in this form: Final Answer: \boxed{...}
|
||||
5. Do not use Markdown code fences.
|
||||
6. Do not switch to a different answer format.
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
repo_id = "zannvznn/qwen3-0.6b-math-l45-qlora-merged-fp16-v2"
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
repo_id,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
```
|
||||
Reference in New Issue
Block a user