Instructions to use FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps")
model = AutoModelForCausalLM.from_pretrained("FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps

SGLang

How to use FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps 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 "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps" \
    --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": "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps",
		"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 "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps" \
        --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": "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps with Docker Model Runner:
```
docker model run hf.co/FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps
```

Fine-tuned Llama Model with GRPO

This model is a fine-tuned version of FrontierInstruments/finetuning_llama_grpo_50_8gpu_1000steps using Group Relative Policy Optimization (GRPO).

Training Details

Base Model: FrontierInstruments/finetuning_llama_grpo_50_8gpu_1000steps
Training Method: GRPO (Group Relative Policy Optimization)
Training Steps: 1000
Dataset: Protocol completion task dataset (FULL)
Hardware: 8x GPU distributed training with DeepSpeed ZeRO-3
Precision: FP16

Model Description

This model has been fine-tuned specifically for protocol completion tasks, using custom reward functions that evaluate:

Semantic correctness of protocol steps
Proper XML format adherence
Step-by-step reasoning quality

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps")

# Generate text
inputs = tokenizer("Your prompt here", return_tensors="pt")
with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Configuration

LoRA rank: 32
LoRA alpha: 64
Learning rate: 1e-5
Batch size: 8 (effective)
Max sequence length: 1024
Beta (GRPO): 0.05

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F16

Model tree for FrontierInstruments/finetuning_llama_grpo_full_8gpu_1000steps

Base model

FrontierInstruments/finetuning_llama_grpo_50_8gpu_1000steps

Finetuned

(1)

this model