Instructions to use iamtarun/pycompetitive-codegen350M-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iamtarun/pycompetitive-codegen350M-qlora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="iamtarun/pycompetitive-codegen350M-qlora")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("iamtarun/pycompetitive-codegen350M-qlora") model = AutoModelForCausalLM.from_pretrained("iamtarun/pycompetitive-codegen350M-qlora") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use iamtarun/pycompetitive-codegen350M-qlora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "iamtarun/pycompetitive-codegen350M-qlora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "iamtarun/pycompetitive-codegen350M-qlora", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/iamtarun/pycompetitive-codegen350M-qlora
- SGLang
How to use iamtarun/pycompetitive-codegen350M-qlora 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 "iamtarun/pycompetitive-codegen350M-qlora" \ --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": "iamtarun/pycompetitive-codegen350M-qlora", "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 "iamtarun/pycompetitive-codegen350M-qlora" \ --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": "iamtarun/pycompetitive-codegen350M-qlora", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use iamtarun/pycompetitive-codegen350M-qlora with Docker Model Runner:
docker model run hf.co/iamtarun/pycompetitive-codegen350M-qlora
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,10 +10,12 @@ pipeline_tag: text-generation
|
|
| 10 |
tags:
|
| 11 |
- code
|
| 12 |
widget:
|
| 13 |
-
- text: "
|
| 14 |
example_title: "Code Example 1"
|
| 15 |
-
- text: "
|
| 16 |
example_title: "Code Example 2"
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# Competitive Programming LLM for Python Language
|
|
|
|
| 10 |
tags:
|
| 11 |
- code
|
| 12 |
widget:
|
| 13 |
+
- text: "def isprime(num):"
|
| 14 |
example_title: "Code Example 1"
|
| 15 |
+
- text: "def binary_search"
|
| 16 |
example_title: "Code Example 2"
|
| 17 |
+
- text: "def square(num):"
|
| 18 |
+
example_title: "Code Example 3"
|
| 19 |
---
|
| 20 |
|
| 21 |
# Competitive Programming LLM for Python Language
|