Text Generation
Transformers
Safetensors
qwen2
verl
math
grpo
transfer
3b
7bi-to-3bi
conversational
text-generation-inference
Instructions to use hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hyunseoki/verl-math-transfer-7bi-to-3bi-fix03") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("hyunseoki/verl-math-transfer-7bi-to-3bi-fix03") model = AutoModelForCausalLM.from_pretrained("hyunseoki/verl-math-transfer-7bi-to-3bi-fix03", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
- SGLang
How to use hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 with Docker Model Runner:
docker model run hf.co/hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
VERL Math Transfer 7B to 3B fix03
Math transfer experiment trained with verl. This repo groups all exported Hugging Face checkpoints for the 7B-to-3B fix_0_3 configuration.
Layout
main: latest exported checkpoint, currentlystep-130- 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
Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
repo_id = "hyunseoki/verl-math-transfer-7bi-to-3bi-fix03"
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-7bi-to-3bi-fix03"
revision = "step-130"
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_modelmetadata is not set automatically. - Checkpoints were exported from verl FSDP shards into Hugging Face
safetensorsformat.
- Downloads last month
- 5