Instructions to use kviai/KviGPT-7b-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kviai/KviGPT-7b-Chat with Transformers:

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

pipe = pipeline("text-generation", model="kviai/KviGPT-7b-Chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kviai/KviGPT-7b-Chat")
model = AutoModelForCausalLM.from_pretrained("kviai/KviGPT-7b-Chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kviai/KviGPT-7b-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kviai/KviGPT-7b-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kviai/KviGPT-7b-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kviai/KviGPT-7b-Chat

SGLang

How to use kviai/KviGPT-7b-Chat 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 "kviai/KviGPT-7b-Chat" \
    --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": "kviai/KviGPT-7b-Chat",
		"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 "kviai/KviGPT-7b-Chat" \
        --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": "kviai/KviGPT-7b-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kviai/KviGPT-7b-Chat with Docker Model Runner:
```
docker model run hf.co/kviai/KviGPT-7b-Chat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

KviGPT 7b

KviGPT - powerful LLM text generation model.

Usage

You can use KVIGPT using transformers library, here it is how:

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kviai/KviGPT-7b-Chat")
model = AutoModelForCausalLM.from_pretrained("kviai/KviGPT-7b-Chat")

prompt = "Hi, what do you know about TON coin?"
output = pipeline(prompt)
print(output)

Model Details

You can train it using Amazon SageMaker or Auto Train

Credits

Developed by: KviAI
Funded byu: Katsyka Vasiliy
Model type: Text Generation
Language(s) (NLP): English
License: Creative Commons Attribution Share Alike 4.0

Demo

Demo: [https://hf.co/spaces/kviai/kvigpt]

Downloads last month: 12

Model tree for kviai/KviGPT-7b-Chat

Quantizations

2 models