37 lines
1.2 KiB
Markdown
37 lines
1.2 KiB
Markdown
|
---
|
||
|
|
license: mit
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model: Qwen/Qwen3-4B
|
||
|
|
tags:
|
||
|
|
- qwen3
|
||
|
|
- ssd
|
||
|
|
- self-distillation
|
||
|
|
- rlve
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen3-4B SSD (RLVE Eval20, N=20) — global step 500
|
||
|
|
|
||
|
|
Weights merged from VERL FSDP SFT checkpoint **`global_step_500`** (500 optimizer steps, 1 epoch schedule) of
|
||
|
|
**Simple Self-Distillation (SSD)** applied to **Qwen/Qwen3-4B**:
|
||
|
|
sample N=20 self-generated responses from the frozen base model, then SFT on those samples.
|
||
|
|
|
||
|
|
## Training data
|
||
|
|
|
||
|
|
Parquet SFT corpus (16k rows, `messages` column):
|
||
|
|
[CL-From-Nothing/RLVE-Eval20-Qwen3-4B-SSD-N20-SFT-Train](https://huggingface.co/datasets/CL-From-Nothing/RLVE-Eval20-Qwen3-4B-SSD-N20-SFT-Train).
|
||
|
|
|
||
|
|
Companion 1.7B model: [CL-From-Nothing/Qwen3-1-7B-SSD-RLVE-Eval20-N20-global-step-500](https://huggingface.co/CL-From-Nothing/Qwen3-1-7B-SSD-RLVE-Eval20-N20-global-step-500).
|
||
|
|
|
||
|
|
## Load
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
|
|
||
|
|
model_id = "CL-From-Nothing/Qwen3-4B-SSD-RLVE-Eval20-N20-global-step-500"
|
||
|
|
tok = AutoTokenizer.from_pretrained(model_id)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
|
||
|
|
```
|