Instructions to use ilsp/Llama-Krikri-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ilsp/Llama-Krikri-8B-Instruct with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ilsp/Llama-Krikri-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("ilsp/Llama-Krikri-8B-Instruct", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ilsp/Llama-Krikri-8B-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ilsp/Llama-Krikri-8B-Instruct

SGLang

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

Docker Model Runner
How to use ilsp/Llama-Krikri-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/ilsp/Llama-Krikri-8B-Instruct
```

MLX Quantization

by Planbch - opened Mar 12, 2025

Discussion

Planbch

Mar 12, 2025

Can you also provide the MLX Quantization of this model?

soksof changed discussion status to closed Mar 12, 2025

soksof changed discussion status to open Mar 12, 2025

soksof

Athena Research Center | Institute for Language and Speech Processing org Mar 12, 2025

Hello, no for the time being there are no plans on providing MLX Quantization of this specific model.

geopar

Athena Research Center | Institute for Language and Speech Processing org 13 days ago

We just uploaded the mlx version:

https://huggingface.co/ilsp/Llama-Krikri-8B-Instruct-4bit-mlx

and for the newer v1.5:

https://huggingface.co/ilsp/Llama-Krikri-8B-Instruct-v1.5-4bit-mlx

soksof changed discussion status to closed 8 days ago

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