49 lines
1.5 KiB
Markdown
49 lines
1.5 KiB
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- verl
|
||
|
|
- math
|
||
|
|
- grpo
|
||
|
|
- transfer
|
||
|
|
- qwen2
|
||
|
|
- 7b
|
||
|
|
- 7bi-to-7bi
|
||
|
|
---
|
||
|
|
|
||
|
|
# VERL Math Transfer 7B to 7B v2
|
||
|
|
|
||
|
|
Math transfer experiment trained with verl. This repo groups all exported Hugging Face checkpoints for the 7B-to-7B v2 configuration.
|
||
|
|
|
||
|
|
## Layout
|
||
|
|
|
||
|
|
- `main`: latest exported checkpoint, currently `step-150`
|
||
|
|
- step revisions: `step-010, step-020, step-030, step-040, step-050, step-060, step-070, step-080, step-090, step-100, step-110, step-120, step-130, step-140, step-150`
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
|
|
||
|
|
repo_id = "hyunseoki/verl-math-transfer-7bi-to-7bi-v2"
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)
|
||
|
|
```
|
||
|
|
|
||
|
|
Load a specific checkpoint revision:
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
|
|
||
|
|
repo_id = "hyunseoki/verl-math-transfer-7bi-to-7bi-v2"
|
||
|
|
revision = "step-150"
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(repo_id, revision=revision, trust_remote_code=True)
|
||
|
|
model = AutoModelForCausalLM.from_pretrained(repo_id, revision=revision, trust_remote_code=True)
|
||
|
|
```
|
||
|
|
|
||
|
|
## Notes
|
||
|
|
|
||
|
|
- Architecture detected from the exported config: `Qwen2ForCausalLM`
|
||
|
|
- The original base model Hub ID is not encoded in these local checkpoints, so `base_model` metadata is not set automatically.
|
||
|
|
- Checkpoints were exported from verl FSDP shards into Hugging Face `safetensors` format.
|