Instructions to use Vipitis/santacoder-finetuned-the-stack-glsl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vipitis/santacoder-finetuned-the-stack-glsl with Transformers:

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

pipe = pipeline("text-generation", model="Vipitis/santacoder-finetuned-the-stack-glsl", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vipitis/santacoder-finetuned-the-stack-glsl", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Vipitis/santacoder-finetuned-the-stack-glsl", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vipitis/santacoder-finetuned-the-stack-glsl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Vipitis/santacoder-finetuned-the-stack-glsl

SGLang

How to use Vipitis/santacoder-finetuned-the-stack-glsl 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 "Vipitis/santacoder-finetuned-the-stack-glsl" \
    --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": "Vipitis/santacoder-finetuned-the-stack-glsl",
		"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 "Vipitis/santacoder-finetuned-the-stack-glsl" \
        --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": "Vipitis/santacoder-finetuned-the-stack-glsl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vipitis/santacoder-finetuned-the-stack-glsl with Docker Model Runner:
```
docker model run hf.co/Vipitis/santacoder-finetuned-the-stack-glsl
```

santacoder-finetuned-the-stack-glsl / README.md

Vipitis

Add base model metadata

5382601 over 2 years ago

preview code

Raw

History Blame Contribute Delete

1.68 kB

	---
	language:
	- code
	license: bigcode-openrail-m
	datasets:
	- bigcode/the-stack-dedup
	pipeline_tag: text-generation
	tags:
	- code
	- shader
	base_model: bigcode/santacoder
	widget:
	- text: void mainImage( out vec4 fragColor, in vec2 fragCoord )
	example_title: mainImage
	group: Shadertoy
	model-index:
	- name: santacoder-finetuned-the-stack-glsl
	results:
	- task:
	type: text-generation
	name: ShaderEval
	dataset:
	type: Vipitis/Shadertoys-fine
	name: Shadertoys-fine
	config: return_completion
	revision: 0.0.2
	metrics:
	- type: exact_match
	value: 0.380
	name: 300 samples, greedy decoding
	verified: false
	---

	[Santacoder](https://huggingface.co/bigcode/santacoder) finetuned on [The-Stack-dedup (GLSL subset)](https://huggingface.co/datasets/bigcode/the-stack-dedup/tree/main/data/glsl) for 1000 steps with a batch size of 2 and full sequence length of 2048.
	adapted finetuning script found [here](./train.py)

	### Finetuning parameters
	```sh
	python3 train.py --model_path "bigcode/santacoder" \
	--dataset_name "bigcode/the-stack-dedup" \
	--subset "data/glsl" \
	--data_column "content" \
	--split "train" \
	--seq_length 2048 \
	--max_steps 1000 \
	--batch_size 2 \
	--gradient_accumulation_steps 4 \
	--learning_rate 5e-5 \
	--num_warmup_steps 100 \
	--eval_freq 100 \
	--save_freq 100 \
	--log_freq 1 \
	--output_dir "checkpoint_dir" \
	--no_fp16

	```

	Main purpose of this model is to explore if finetuning models improves performance on [ShaderEval](https://huggingface.co/spaces/Vipitis/ShaderEval), which reached 0.380 with 300 samples.

	License carried over from model, and the finetuning dataset holds the same license.