Instructions to use TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ

SGLang

How to use TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ 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 "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ" \
    --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": "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ",
		"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 "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ" \
        --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": "TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeNinja-1.0-OpenChat-7B-GPTQ
```

Godot Coding

by IggyLux - opened Feb 1, 2024

Discussion

IggyLux

Feb 1, 2024

I asked it for instructions regarding Godot, specifically 4.0. It acknowledged that it knew 4.0 and then proceeded to give me instructions on how to use Unity.
So, while it might be great at coding. Even after asking if it was wrong and if it was Unity it still proceeded to give me directions in Unity thinking it was Godot.

I'm sure programming wise its great, but logic regarding versions/engines did not seem all that good. I'll continue to play around with it, but just figured I'd share my experience.

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