Instructions to use openmuse/sample_8B_r2006_seed123 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openmuse/sample_8B_r2006_seed123 with Transformers:

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

pipe = pipeline("text-generation", model="openmuse/sample_8B_r2006_seed123")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openmuse/sample_8B_r2006_seed123")
model = AutoModelForCausalLM.from_pretrained("openmuse/sample_8B_r2006_seed123", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openmuse/sample_8B_r2006_seed123 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openmuse/sample_8B_r2006_seed123"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openmuse/sample_8B_r2006_seed123",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openmuse/sample_8B_r2006_seed123

SGLang

How to use openmuse/sample_8B_r2006_seed123 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 "openmuse/sample_8B_r2006_seed123" \
    --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": "openmuse/sample_8B_r2006_seed123",
		"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 "openmuse/sample_8B_r2006_seed123" \
        --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": "openmuse/sample_8B_r2006_seed123",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openmuse/sample_8B_r2006_seed123 with Docker Model Runner:
```
docker model run hf.co/openmuse/sample_8B_r2006_seed123
```

sample_8B_r2006_seed123

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the sample_r2006 dataset. It achieves the following results on the evaluation set:

Loss: 0.9557
Num Input Tokens Seen: 1045040544

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 1
seed: 123
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 32
total_train_batch_size: 512
total_eval_batch_size: 4
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
training_steps: 250

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
1.6994	0.2575	50	0.9550	209689600
1.689	0.5150	100	0.9602	419379200
1.694	0.7724	150	0.9509	629068800
1.6407	1.0257	200	0.9585	835350944
1.6166	1.2832	250	0.9557	1045040544

Framework versions

Transformers 4.51.0
Pytorch 2.7.1+cu128
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: 19

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for openmuse/sample_8B_r2006_seed123

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1504)

this model