Instructions to use beratcmn/Llama3-ChatQA-1.5-8B-256K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beratcmn/Llama3-ChatQA-1.5-8B-256K with Transformers:

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

pipe = pipeline("text-generation", model="beratcmn/Llama3-ChatQA-1.5-8B-256K")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beratcmn/Llama3-ChatQA-1.5-8B-256K")
model = AutoModelForCausalLM.from_pretrained("beratcmn/Llama3-ChatQA-1.5-8B-256K", device_map="auto")

PEFT
How to use beratcmn/Llama3-ChatQA-1.5-8B-256K with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use beratcmn/Llama3-ChatQA-1.5-8B-256K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beratcmn/Llama3-ChatQA-1.5-8B-256K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beratcmn/Llama3-ChatQA-1.5-8B-256K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/beratcmn/Llama3-ChatQA-1.5-8B-256K

SGLang

How to use beratcmn/Llama3-ChatQA-1.5-8B-256K 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 "beratcmn/Llama3-ChatQA-1.5-8B-256K" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beratcmn/Llama3-ChatQA-1.5-8B-256K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "beratcmn/Llama3-ChatQA-1.5-8B-256K" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beratcmn/Llama3-ChatQA-1.5-8B-256K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use beratcmn/Llama3-ChatQA-1.5-8B-256K with Docker Model Runner:
```
docker model run hf.co/beratcmn/Llama3-ChatQA-1.5-8B-256K
```

Llama3-ChatQA-1.5-8B-256K

I tried to achive long context RAG pipeline with this model but I have very limited resources to test this workflow. Keep in mind that this is an experimentation.

This model is an 'amalgamation' of winglian/llama-3-8b-256k-PoSE and nvidia/Llama3-ChatQA-1.5-8B.

Recipe

First I extracted the Lora adapter from nvidia/Llama3-ChatQA-1.5-8B using mergekkit. You can find the adapter here.

After the extraction I merged the adapter with the winglian/llama-3-8b-256k-PoSE model.

Prompt Format

Since base model wasn't finetuned for any specific format we can use the ChatQA's chat format.

System: {System}

{Context}

User: {Question}

Assistant: {Response}

User: {Question}

Assistant:

Big thanks to Meta Team, Nvidia Team and of course Wing Lian.

Notes

This model has not been tested on any benchmarks due to compute limitations. Base model wasn't evaluated using Needle in Haystack as well. There is a big possibility that this model might perform worse than both of the original models.

Downloads last month: 30

Safetensors

Model size

8B params

Tensor type

F16

Model tree for beratcmn/Llama3-ChatQA-1.5-8B-256K

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

(607)

this model