Instructions to use Buggod/OpenRS-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Buggod/OpenRS-GRPO with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Buggod/OpenRS-GRPO")
model = AutoModelForCausalLM.from_pretrained("Buggod/OpenRS-GRPO")
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 Buggod/OpenRS-GRPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Buggod/OpenRS-GRPO

SGLang

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

Docker Model Runner
How to use Buggod/OpenRS-GRPO with Docker Model Runner:
```
docker model run hf.co/Buggod/OpenRS-GRPO
```

Buggod commited on Apr 11, 2025

Commit

9cc53ff

verified ·

1 Parent(s): 22a8539

Training in progress, step 50

Browse files

Files changed (6) hide show

.ipynb_checkpoints/all_results-checkpoint.json +8 -0
.ipynb_checkpoints/generation_config-checkpoint.json +9 -0
.ipynb_checkpoints/train_results-checkpoint.json +8 -0
config.json +1 -1
model.safetensors +1 -1
training_args.bin +2 -2

.ipynb_checkpoints/all_results-checkpoint.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "total_flos": 0.0,
+    "train_loss": 0.16526810049655613,
+    "train_runtime": 49656.4521,
+    "train_samples": 7000,
+    "train_samples_per_second": 0.483,
+    "train_steps_per_second": 0.01
+}

.ipynb_checkpoints/generation_config-checkpoint.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.50.0"
+}

.ipynb_checkpoints/train_results-checkpoint.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "total_flos": 0.0,
+    "train_loss": 0.16526810049655613,
+    "train_runtime": 49656.4521,
+    "train_samples": 7000,
+    "train_samples_per_second": 0.483,
+    "train_steps_per_second": 0.01
+}

config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
-  "use_cache": true,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936

   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51c29c6ff6aa4c71fa2667d4813595081aaeb49489769e7df8845cd682538d2a
 size 3554214752

 version https://git-lfs.github.com/spec/v1
+oid sha256:5802e312c34f55feb031067c11668f23a4d765ebb4b8b2f8022360c38c4228e4
 size 3554214752

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a3c6b46281b4adeff4678921308ef393abea46e619b88e7865c81196c32f86
-size 8568

 version https://git-lfs.github.com/spec/v1
+oid sha256:77372817777ee57a39496dcf790c82cf535ccb75d7e464e4f98eb6cf7d9fece5
+size 8376