Instructions to use Crystalcareai/llama-3-4x8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Crystalcareai/llama-3-4x8b with Transformers:

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

pipe = pipeline("text-generation", model="Crystalcareai/llama-3-4x8b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Crystalcareai/llama-3-4x8b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Crystalcareai/llama-3-4x8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Crystalcareai/llama-3-4x8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Crystalcareai/llama-3-4x8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Crystalcareai/llama-3-4x8b

SGLang

How to use Crystalcareai/llama-3-4x8b 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 "Crystalcareai/llama-3-4x8b" \
    --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": "Crystalcareai/llama-3-4x8b",
		"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 "Crystalcareai/llama-3-4x8b" \
        --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": "Crystalcareai/llama-3-4x8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Crystalcareai/llama-3-4x8b with Docker Model Runner:
```
docker model run hf.co/Crystalcareai/llama-3-4x8b
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This is an MOE of Llama-3-8b with 4 experts. This does not use semantic routing, as this utilizes the deepseek-moe architecture. There is no routing, and there is no gate - all experts are active on every token.

import torch
from transformers import AutoTokenizer, TextStreamer, AutoModelForCausalLM

model_path = "Crystalcareai/llama-3-4x8b"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    low_cpu_mem_usage=True,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
    attn_implementation="flash_attention_2",
)

tokenizer = AutoTokenizer.from_pretrained(model_path)
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

# Modify the prompt to match the Alpaca instruction template
prompt = """
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
Sam is faster than Joe. Joe is faster than Jane. Is Sam faster than Jane? Explain your reasoning step by step.

### Input:

### Response:
"""

tokens = tokenizer(
    prompt, 
    return_tensors='pt'
).input_ids.cuda()

generation_output = model.generate(
    tokens, 
    streamer=streamer,
    max_new_tokens=512,
)

Downloads last month: 51

Safetensors

Model size

31B params

Tensor type

F16