Instructions to use AceofStades/dsc-co-grpo-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AceofStades/dsc-co-grpo-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-3B-Instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "AceofStades/dsc-co-grpo-lora")

Transformers

How to use AceofStades/dsc-co-grpo-lora with Transformers:

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

pipe = pipeline("text-generation", model="AceofStades/dsc-co-grpo-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AceofStades/dsc-co-grpo-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AceofStades/dsc-co-grpo-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AceofStades/dsc-co-grpo-lora

SGLang

How to use AceofStades/dsc-co-grpo-lora 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 "AceofStades/dsc-co-grpo-lora" \
    --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": "AceofStades/dsc-co-grpo-lora",
		"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 "AceofStades/dsc-co-grpo-lora" \
        --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": "AceofStades/dsc-co-grpo-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use AceofStades/dsc-co-grpo-lora with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AceofStades/dsc-co-grpo-lora to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AceofStades/dsc-co-grpo-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AceofStades/dsc-co-grpo-lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="AceofStades/dsc-co-grpo-lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use AceofStades/dsc-co-grpo-lora with Docker Model Runner:
```
docker model run hf.co/AceofStades/dsc-co-grpo-lora
```

dsc-co-grpo-lora

LoRA adapter trained with TRL GRPO + Unsloth for openenv-dsc-co, a 30-step supply-chain planning environment verified by a deterministic Pulp/CBC min-cost-flow oracle.

Training Setup

Base model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
Method: 4-bit QLoRA, LoRA rank 32
Trainer: TRL GRPOTrainer
Samples: 2,000 prompts
Steps: 400
Generations per prompt: 8
Max completion length: 768
Runtime: 17,469.9 seconds / 4h 51m
Final train loss: -0.04913

Reward Evidence

metric	first logged step	final step	best / aggregate
combined reward	0.622	1.304	max 1.365
cumulative env reward	0.505	0.852	last-25 mean 0.855
terminal MILP reward	0.052	0.226	max 0.241
reward std	0.387	0.079	`frac_reward_zero_std=0` final
KL	0.000	0.0077	stable

The terminal reward is emitted only after the environment reaches the 30-step horizon and invokes the MILP verifier. Non-zero terminal reward throughout the run confirms the model-generated tool actions reached verified episode completion, not just dense shaping events.

Loading

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "AceofStades/dsc-co-grpo-lora",
    max_seq_length=8192,
    load_in_4bit=True,
    fast_inference=True,
)
FastLanguageModel.for_inference(model)

Notes

The model is a planning-policy adapter for the DSC environment. It is not a general-purpose assistant model. The environment and reward pipeline are documented in the source README and linked docs.

Downloads last month: -

Model tree for AceofStades/dsc-co-grpo-lora

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

unsloth/Llama-3.2-3B-Instruct-bnb-4bit

Adapter

(49)

this model

AceofStades
/

dsc-co-grpo-lora