Not-For-All-Audiences

Instructions to use Hastagaras/Halu-8B-Llama3-Blackroot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hastagaras/Halu-8B-Llama3-Blackroot with Transformers:

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

pipe = pipeline("text-generation", model="Hastagaras/Halu-8B-Llama3-Blackroot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Hastagaras/Halu-8B-Llama3-Blackroot")
model = AutoModelForMultimodalLM.from_pretrained("Hastagaras/Halu-8B-Llama3-Blackroot")
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 Hastagaras/Halu-8B-Llama3-Blackroot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hastagaras/Halu-8B-Llama3-Blackroot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hastagaras/Halu-8B-Llama3-Blackroot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hastagaras/Halu-8B-Llama3-Blackroot

SGLang

How to use Hastagaras/Halu-8B-Llama3-Blackroot 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 "Hastagaras/Halu-8B-Llama3-Blackroot" \
    --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": "Hastagaras/Halu-8B-Llama3-Blackroot",
		"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 "Hastagaras/Halu-8B-Llama3-Blackroot" \
        --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": "Hastagaras/Halu-8B-Llama3-Blackroot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hastagaras/Halu-8B-Llama3-Blackroot with Docker Model Runner:
```
docker model run hf.co/Hastagaras/Halu-8B-Llama3-Blackroot
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

EXPERIMENTAL MODEL

VERY IMPORTANT: This model has not been extensively tested or evaluated, and its performance characteristics are currently unknown. It may generate harmful, biased, or inappropriate content. Please exercise caution and use it at your own risk and discretion.

I just tried saishf's merged model, and it's great. So I decided to try a similar merge method with Blackroot's LoRA that I had found earlier.

I don't know what to say about this model... this model is very strange...Maybe because Blackroot's amazing Loras used human data and not synthetic data, hence the model turned out to be very human-like...even the actions or narrations.

WARNING: This model is very unsafe in certain parts...especially in RP.

IMATRIX GGUF IS HERE made available by Lewdiculous

STATIC GGUF IS HERE made avaible by mradermacher

Merge Method

This model was merged using the Model Stock merge method using Hastagaras/Halu-8B-Llama3-v0.3 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: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-LongStory-LORA
  - model: Hastagaras/Halu-8B-Llama3-v0.3+Blackroot/Llama-3-8B-Abomination-LORA
merge_method: model_stock
base_model: Hastagaras/Halu-8B-Llama3-v0.3
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	69.78
AI2 Reasoning Challenge (25-Shot)	63.82
HellaSwag (10-Shot)	84.55
MMLU (5-Shot)	67.04
TruthfulQA (0-shot)	53.28
Winogrande (5-shot)	79.48
GSM8k (5-shot)	70.51