Instructions to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-coder-7b-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned")

Transformers

How to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned with Transformers:

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

pipe = pipeline("text-generation", model="KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned

SGLang

How to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned 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 "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned" \
    --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": "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned",
		"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 "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned" \
        --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": "KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned with Docker Model Runner:
```
docker model run hf.co/KarthikRagunathAnandaKumar/LearningToPresent-RL-Qwen-2.5B-Coder-Instruct-GRPO-Finetuned
```

KarthikRagunathAnandaKumar commited on Mar 18

Commit

367f79a

verified ·

1 Parent(s): 9495534

Remove HTML from model description

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ model-index:
 # LearningToPresent-RL-Qwen-2.5-Coder-7B-Instruct-GRPO-Finetuned
-A GRPO-finetuned LoRA adapter for [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), trained to generate professional HTML slide presentations through multi-turn tool use in a reinforcement learning environment.
 The model achieves **91.2% of Claude Opus 4.6's quality score** (0.724 vs. 0.794) while improving **33.1% over the untuned base model** (0.544), using only **0.53% trainable parameters** (40.4M out of 7.62B).

 # LearningToPresent-RL-Qwen-2.5-Coder-7B-Instruct-GRPO-Finetuned
+A GRPO-finetuned LoRA adapter for [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), trained to generate professional slide presentations through multi-turn tool use in a reinforcement learning environment.
 The model achieves **91.2% of Claude Opus 4.6's quality score** (0.724 vs. 0.794) while improving **33.1% over the untuned base model** (0.544), using only **0.53% trainable parameters** (40.4M out of 7.62B).