verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1/README.md

library_name, pipeline_tag, tags

library_name	pipeline_tag	tags
transformers	text-generation	verl math grpo transfer llama llama-3.1 llama-3.2 8b 3b pool7to1

VERL Math Transfer Llama 3.1 8B to Llama 3.2 3B pool7to1

Math transfer experiment trained with verl. This repo groups all exported Hugging Face checkpoints for the Llama 3.1 8B to Llama 3.2 3B pool7to1 configuration.

Layout

• main: latest exported checkpoint, currently step-080
• step revisions: step-010, step-020, step-030, step-040, step-050, step-060, step-070, step-080

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1"
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:

from transformers import AutoTokenizer, AutoModelForCausalLM

repo_id = "hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1"
revision = "step-080"
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: LlamaForCausalLM
• 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.