Instructions to use ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72 with Transformers:

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

pipe = pipeline("text-generation", model="ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72")
model = AutoModelForCausalLM.from_pretrained("ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72")
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 ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72

SGLang

How to use ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72 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 "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72" \
    --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": "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72",
		"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 "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72" \
        --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": "ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72 with Docker Model Runner:
```
docker model run hf.co/ChaoticNeutrals/Hathor_Aleph-L3-8B-v0.72
```

The Instruct preset

by ABX-AI - opened Jul 1, 2024

Discussion

ABX-AI

Jul 1, 2024

I'm super curious what motivated you to leave the sys prompt empty on your aleph instruct set? It does seem to be working reliably well without it but I still wanted to ask if you came to this after testing or maybe some research indicating it?

Nitral-AI

The Chaotic Neutrals org Jul 1, 2024

I'm super curious what motivated you to leave the sys prompt empty on your aleph instruct set? It does seem to be working reliably well without it but I still wanted to ask if you came to this after testing or maybe some research indicating it?

It's a test currently funny enough: I find there are two extremes - One where the system-prompt seems to have 0 effect, and another where the system prompt seems to have a huge effect. So id recommend people try both with and without a system prompt.

ABX-AI

Jul 1, 2024

I'm super curious what motivated you to leave the sys prompt empty on your aleph instruct set? It does seem to be working reliably well without it but I still wanted to ask if you came to this after testing or maybe some research indicating it?

It's a test currently funny enough: I find there are two extremes - One where the system-prompt seems to have 0 effect, and another where the system prompt seems to have a huge effect. So id recommend people try both with and without a system prompt.

I see, thanks :) I was thinking about this for a bit and whether it's better to go minimal or maximal with the sys prompt. Up until now, I think the sense I got is that minimal prompts work better with accuracy of the cards, but longer prompts may work better with big models (70b and above?) where situational awareness is better and the sys prompt is followed better as well.

Stuff like "keep track of what's going on" doesn't seem to do much with smaller models like 7-9b. I'm still not sure about it tbh but minimal has the advantage of extra context space, if anything ^^

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