Instructions to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with Transformers:

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

pipe = pipeline("text-generation", model="failspy/Meta-Llama-3-8B-Instruct-abliterated-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("failspy/Meta-Llama-3-8B-Instruct-abliterated-v3")
model = AutoModelForMultimodalLM.from_pretrained("failspy/Meta-Llama-3-8B-Instruct-abliterated-v3")
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 failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3

SGLang

How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 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 "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3" \
    --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": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"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 "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3" \
        --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": "failspy/Meta-Llama-3-8B-Instruct-abliterated-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 with Docker Model Runner:
```
docker model run hf.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
```

Alternative quantizatioons.

by ZeroWw - opened Jun 28, 2024

Discussion

ZeroWw

Jun 28, 2024

https://huggingface.co/ZeroWw/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF

My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.

Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.

ZeroWw

Jun 29, 2024

@failspy hello! thanks for the abliterated versions.. can you please also do this one: https://huggingface.co/gradientai/Llama-3-8B-Instruct-Gradient-4194k

And, mistral instruct v03?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment