Instructions to use Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle with Transformers:

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

pipe = pipeline("text-generation", model="Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle")
model = AutoModelForMultimodalLM.from_pretrained("Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle")
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 Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle

SGLang

How to use Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle 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 "Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle" \
    --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": "Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle",
		"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 "Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle" \
        --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": "Dampfinchen/Llama-3-8B-Ultra-Instruct-SaltSprinkle",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using NousResearch/Meta-Llama-3-8B 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: NousResearch/Meta-Llama-3-8B-Instruct
    parameters:
      density: 1
      weight: 1
  - model: Dampfinchen/Llama-3-8B-Ultra-Instruct
    parameters:
      density: 0.5
      weight: 0.2

merge_method: dare_ties
base_model: NousResearch/Meta-Llama-3-8B
dtype: bfloat16

Test of salt sprinkle methode. The goal is to retain all of L3 Instruct's capabilities while adding better RP, RAG, German and story writing capabilities in the form of Ultra Instruct. Model may generate harmful responses, I'm not responsible for what you do with this model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.61
AI2 Reasoning Challenge (25-Shot)	61.35
HellaSwag (10-Shot)	77.76
MMLU (5-Shot)	67.88
TruthfulQA (0-shot)	52.82
Winogrande (5-shot)	74.98
GSM8k (5-shot)	70.89