Instructions to use nbeerbower/llama-3-stinky-v2-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/llama-3-stinky-v2-8B with Transformers:

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

pipe = pipeline("text-generation", model="nbeerbower/llama-3-stinky-v2-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nbeerbower/llama-3-stinky-v2-8B")
model = AutoModelForCausalLM.from_pretrained("nbeerbower/llama-3-stinky-v2-8B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nbeerbower/llama-3-stinky-v2-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nbeerbower/llama-3-stinky-v2-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nbeerbower/llama-3-stinky-v2-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nbeerbower/llama-3-stinky-v2-8B

SGLang

How to use nbeerbower/llama-3-stinky-v2-8B 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 "nbeerbower/llama-3-stinky-v2-8B" \
    --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": "nbeerbower/llama-3-stinky-v2-8B",
		"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 "nbeerbower/llama-3-stinky-v2-8B" \
        --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": "nbeerbower/llama-3-stinky-v2-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nbeerbower/llama-3-stinky-v2-8B with Docker Model Runner:
```
docker model run hf.co/nbeerbower/llama-3-stinky-v2-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llama-3-stinky-v2-8B

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using flammenai/Mahou-1.1-llama3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/ChimeraLlama-3-8B-v2
  - model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
  - model: nbeerbower/llama-3-stella-8B
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
  - model: uygarkurt/llama-3-merged-linear
  - model: openlynn/Llama-3-Soliloquy-8B-v2
  - model: grimjim/llama-3-merge-pp-instruct-8B
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
  - model: grimjim/llama-3-merge-virt-req-8B
  - model: jeiku/Orthocopter_8B
  - model: grimjim/llama-3-nvidia-ChatQA-1.5-8B
  - model: flammenai/Mahou-1.0-llama3-8B
merge_method: model_stock
base_model: flammenai/Mahou-1.1-llama3-8B
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.27
AI2 Reasoning Challenge (25-Shot)	66.98
HellaSwag (10-Shot)	83.20
MMLU (5-Shot)	68.33
TruthfulQA (0-shot)	55.83
Winogrande (5-shot)	77.51
GSM8k (5-shot)	69.75