Instructions to use Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw with Transformers:

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

pipe = pipeline("text-generation", model="Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw")
model = AutoModelForMultimodalLM.from_pretrained("Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw

SGLang

How to use Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw 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 "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw" \
    --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": "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw",
		"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 "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw" \
        --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": "Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw with Docker Model Runner:
```
docker model run hf.co/Dracones/EVA-LLaMA-3.33-70B-v0.0_exl2_4.0bpw
```

V0.1 at 4.0-4.25bpw?

by Surprisekitty - opened Feb 17, 2025

Discussion

Surprisekitty

Feb 17, 2025

Howdy! I love your work. I was wondering if EVA-LLaMA-3.33-70B-v0.1 was on the table? The only EXL2 quant around for that model is 5.0bpw, and I would be really grateful if a 4.0-4.25bpw was made. If not, no worries - just wanted to put the suggestion out there.

Dracones

Owner Feb 19, 2025

Added: https://huggingface.co/Dracones/EVA-LLaMA-3.33-70B-v0.1_exl2_4.0bpw

Dracones changed discussion status to closed Feb 19, 2025

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