Instructions to use sahil2801/instruct-codegen-16B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sahil2801/instruct-codegen-16B with Transformers:

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

pipe = pipeline("text-generation", model="sahil2801/instruct-codegen-16B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sahil2801/instruct-codegen-16B")
model = AutoModelForCausalLM.from_pretrained("sahil2801/instruct-codegen-16B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sahil2801/instruct-codegen-16B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sahil2801/instruct-codegen-16B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sahil2801/instruct-codegen-16B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sahil2801/instruct-codegen-16B

SGLang

How to use sahil2801/instruct-codegen-16B 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 "sahil2801/instruct-codegen-16B" \
    --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": "sahil2801/instruct-codegen-16B",
		"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 "sahil2801/instruct-codegen-16B" \
        --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": "sahil2801/instruct-codegen-16B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sahil2801/instruct-codegen-16B with Docker Model Runner:
```
docker model run hf.co/sahil2801/instruct-codegen-16B
```

instruct-codegen-16B / README.md

sahil2801

Update README.md

b2d94bc about 3 years ago

preview code

Raw

History Blame Contribute Delete

1.61 kB

	---
	license: bsd-3-clause
	metrics:
	- code_eval
	pipeline_tag: text-generation
	tags:
	- code
	model-index:
	- name: instruct-codegen-16B
	results:
	- task:
	type: code-generation
	dataset:
	type: openai_humaneval
	name: HumanEval
	metrics:
	- name: pass@1
	type: pass@1
	value: 0.371
	verified: false
	---
	# Model Card for instruct-codegen-16B

	<!-- Provide a quick summary of what the model is/does. -->

	Instruct-codegen-16B is an instruction following codegen model based on [Salesforce codegen-16B-multi](https://huggingface.co/Salesforce/codegen-16B-multi) , finetuned on a dataset of 250k instruction-following samples in the alpaca format.

	The data was not generated using any commercial LLM api.

	The model achieves a result of 37.1% pass@1 on the HumanEval benchmark.

	## Generation

	```python
	# pip install -q transformers
	from transformers import AutoModelForCausalLM, AutoTokenizer
	checkpoint = "sahil2801/instruct-codegen-16B"
	device = "cuda"
	tokenizer = AutoTokenizer.from_pretrained(checkpoint)
	model = AutoModelForCausalLM.from_pretrained(checkpoint).half().to(device)
	instruction = "Write a function to scrape hacker news."
	prompt = f"Below is an instruction that describes a task.\n Write a response that appropriately completes the request.\n\n ### Instruction:\n{instruction}\n\n### Response:"
	inputs = tokenizer(prompt, return_tensors="pt").to(device)
	outputs = model.generate(**inputs,temperature=0.3,do_sample=True,max_new_tokens=256)
	print(tokenizer.decode(outputs[0],skip_special_tokens=True))
	```