Instructions to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-1025-7B")
model = PeftModel.from_pretrained(base_model, "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php")

Transformers

How to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php with Transformers:

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

pipe = pipeline("text-generation", model="MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php

SGLang

How to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php 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 "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php" \
    --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": "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php",
		"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 "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php" \
        --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": "MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php with Docker Model Runner:
```
docker model run hf.co/MultilingualUnigramLM/ft-code-las-olmo3-7b-thestack100M-php
```

ft-code-las-olmo3-7b-thestack100M-php / adapter_model.safetensors

suchirsalhan

Upload folder using huggingface_hub

a019298 verified about 2 months ago

download

history blame contribute delete

160 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 7fe65f849879fd3638995ad218e1f530f25d4487336fdef9f01ffdc05bdb033b
Size of remote file:: 160 MB
SHA256:: 411b1dfed85a367e3e0df310c0f1c0a4d9657b2439ba37528620188458e3538f

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.