Instructions to use webslate/gitai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webslate/gitai with Transformers:

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

pipe = pipeline("text-generation", model="webslate/gitai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webslate/gitai")
model = AutoModelForCausalLM.from_pretrained("webslate/gitai", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use webslate/gitai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/webslate/gitai

SGLang

How to use webslate/gitai 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 "webslate/gitai" \
    --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": "webslate/gitai",
		"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 "webslate/gitai" \
        --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": "webslate/gitai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use webslate/gitai with Docker Model Runner:
```
docker model run hf.co/webslate/gitai
```

gitai / README.md

ai-venkat-r

Upload 10 files (#1)

53583f8 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.37 kB

	---
	language:
	- en
	license: apache-2.0
	tags:
	- chat
	- code
	pipeline_tag: text-generation
	datasets:
	- YashJain/GitAI
	library_name: transformers
	---

	# YashJain/GitAI-Qwen2-0.5B-Instruct


	## Requirements
	The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
	```
	KeyError: 'qwen2'
	```
	## Quickstart
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	device = "cuda" # the device to load the model onto

	model = AutoModelForCausalLM.from_pretrained(
	"YashJain/GitAI-Qwen2-0.5B-Instruct",
	torch_dtype="auto",
	device_map="auto"
	)
	tokenizer = AutoTokenizer.from_pretrained("YashJain/GitAI-Qwen2-0.5B-Instruct")

	prompt = "How to undo my last commit"
	messages = [
	{"role": "system", "content": "You are a helpful assistant."},
	{"role": "user", "content": prompt}
	]
	text = tokenizer.apply_chat_template(
	messages,
	tokenize=False,
	add_generation_prompt=True
	)
	model_inputs = tokenizer([text], return_tensors="pt").to(device)

	generated_ids = model.generate(
	model_inputs.input_ids,
	max_new_tokens=512
	)
	generated_ids = [
	output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
	]

	response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
	```