Instructions to use neginr/OpenR1-Math-Raw-all-correct-5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neginr/OpenR1-Math-Raw-all-correct-5k with Transformers:

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

pipe = pipeline("text-generation", model="neginr/OpenR1-Math-Raw-all-correct-5k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("neginr/OpenR1-Math-Raw-all-correct-5k")
model = AutoModelForCausalLM.from_pretrained("neginr/OpenR1-Math-Raw-all-correct-5k")
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

vLLM

How to use neginr/OpenR1-Math-Raw-all-correct-5k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neginr/OpenR1-Math-Raw-all-correct-5k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neginr/OpenR1-Math-Raw-all-correct-5k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neginr/OpenR1-Math-Raw-all-correct-5k

SGLang

How to use neginr/OpenR1-Math-Raw-all-correct-5k 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 "neginr/OpenR1-Math-Raw-all-correct-5k" \
    --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": "neginr/OpenR1-Math-Raw-all-correct-5k",
		"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 "neginr/OpenR1-Math-Raw-all-correct-5k" \
        --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": "neginr/OpenR1-Math-Raw-all-correct-5k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use neginr/OpenR1-Math-Raw-all-correct-5k with Docker Model Runner:
```
docker model run hf.co/neginr/OpenR1-Math-Raw-all-correct-5k
```

neginr commited on Apr 28, 2025

Commit

abdead8

verified ·

1 Parent(s): 8832da6

End of training

Browse files

Files changed (4) hide show

README.md +1 -1
all_results.json +3 -3
train_results.json +3 -3
trainer_state.json +3 -3

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # OpenR1-Math-Raw-all-correct-5k
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
 ## Model description

 # OpenR1-Math-Raw-all-correct-5k
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the neginr/OpenR1-Math-Raw-all-correct-5k dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5246,
-    "train_samples_per_second": 13863.535,
-    "train_steps_per_second": 144.181
 }

     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
+    "train_runtime": 2.6671,
+    "train_samples_per_second": 13122.755,
+    "train_steps_per_second": 136.477
 }

train_results.json CHANGED Viewed

@@ -2,7 +2,7 @@
     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
-    "train_runtime": 2.5246,
-    "train_samples_per_second": 13863.535,
-    "train_steps_per_second": 144.181
 }

     "epoch": 6.955414012738854,
     "total_flos": 3.947982283988664e+17,
     "train_loss": 0.0,
+    "train_runtime": 2.6671,
+    "train_samples_per_second": 13122.755,
+    "train_steps_per_second": 136.477
 }

trainer_state.json CHANGED Viewed

@@ -2561,9 +2561,9 @@
       "step": 364,
       "total_flos": 3.947982283988664e+17,
       "train_loss": 0.0,
-      "train_runtime": 2.5246,
-      "train_samples_per_second": 13863.535,
-      "train_steps_per_second": 144.181
     }
   ],
   "logging_steps": 1,

       "step": 364,
       "total_flos": 3.947982283988664e+17,
       "train_loss": 0.0,
+      "train_runtime": 2.6671,
+      "train_samples_per_second": 13122.755,
+      "train_steps_per_second": 136.477
     }
   ],
   "logging_steps": 1,