base_model, library_name, tags

base_model	library_name	tags
meta-llama/Llama-3.2-3B-Instruct	transformers	llama verl fsdp

hill_8k_300

This repository contains the global_step_300 actor checkpoint from the HiLL 8k run, converted from verl FSDP shards to Hugging Face Transformers format.

Source

• Base model: meta-llama/Llama-3.2-3B-Instruct
• Training run: HiLL-Llama-3.2-3B-Instruct-8k
• Checkpoint: global_step_300/actor
• Conversion backend: verl FSDP model merger

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "sagnikM/hill_8k_300"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16)