Instructions to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with Transformers:

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

pipe = pipeline("text-generation", model="rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
model = AutoModelForCausalLM.from_pretrained("rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean")
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 rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean

SGLang

How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean 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 "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean" \
    --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": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"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 "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean" \
        --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": "rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean with Docker Model Runner:
```
docker model run hf.co/rkumar1999/Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
```

rkumar1999 commited on Mar 3, 2025

Commit

e2fe931

verified ·

1 Parent(s): e057e94

End of training

Browse files

Files changed (2) hide show

README.md +3 -1
config.json +41 -0

README.md CHANGED Viewed

@@ -1,9 +1,11 @@
 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
 library_name: transformers
 model_name: Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 tags:
 - generated_from_trainer
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 # Model Card for Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
+datasets: Tonic/MiniF2F
 library_name: transformers
 model_name: Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
 # Model Card for Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [Tonic/MiniF2F](https://huggingface.co/datasets/Tonic/MiniF2F) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start

config.json ADDED Viewed

	@@ -0,0 +1,41 @@

+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}