Instructions to use uukuguy/speechless-tora-code-7b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uukuguy/speechless-tora-code-7b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="uukuguy/speechless-tora-code-7b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uukuguy/speechless-tora-code-7b-v1.0")
model = AutoModelForCausalLM.from_pretrained("uukuguy/speechless-tora-code-7b-v1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use uukuguy/speechless-tora-code-7b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uukuguy/speechless-tora-code-7b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uukuguy/speechless-tora-code-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/uukuguy/speechless-tora-code-7b-v1.0

SGLang

How to use uukuguy/speechless-tora-code-7b-v1.0 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 "uukuguy/speechless-tora-code-7b-v1.0" \
    --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": "uukuguy/speechless-tora-code-7b-v1.0",
		"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 "uukuguy/speechless-tora-code-7b-v1.0" \
        --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": "uukuguy/speechless-tora-code-7b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use uukuguy/speechless-tora-code-7b-v1.0 with Docker Model Runner:
```
docker model run hf.co/uukuguy/speechless-tora-code-7b-v1.0
```

What prompt template(s) do your models use?

by TheBloke - opened Oct 13, 2023

Discussion

TheBloke

Oct 13, 2023

Is there a suggested way to prompt this model, and your Mistral ones?

Or is it purely code completion?

Thanks

uukuguy

Owner Oct 13, 2023

There are no additional special prompt templates. The instruction data from the 30K WizardLM dataset, 40K other Python Evol-Instruct data , and the inference instruction data from Airoboros and Orca were used for model fine-tuning. The HumanEval score improved from 37.8 in the original model to 51.8. For code generation, you can refer to HumanEval.

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