Instructions to use legesher/language-decoded-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use legesher/language-decoded-lora with Transformers:

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

pipe = pipeline("text-generation", model="legesher/language-decoded-lora")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("legesher/language-decoded-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use legesher/language-decoded-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/legesher/language-decoded-lora

SGLang

How to use legesher/language-decoded-lora 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 "legesher/language-decoded-lora" \
    --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": "legesher/language-decoded-lora",
		"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 "legesher/language-decoded-lora" \
        --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": "legesher/language-decoded-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use legesher/language-decoded-lora with Docker Model Runner:
```
docker model run hf.co/legesher/language-decoded-lora
```

rename: condition-3 adapter folders to condition-3-zh-5k-seed{42,123}

#23

by madiedgar - opened 10 days ago

base: refs/heads/main

←

from: refs/pr/23

Discussion Files changed

-3

madiedgar

Legesher org 10 days ago

Renames the two condition-3 adapter folders so every adapter follows one rule: {data config}-seed{seed}, the name the training notebook uploads under.

tiny-aya-base/condition-3-zh-5k-native-code-seed42/ to tiny-aya-base/condition-3-zh-5k-seed42/
tiny-aya-base/condition-3-zh-5k-native-code-seed123/ to tiny-aya-base/condition-3-zh-5k-seed123/

Files are copied server side and the old folders deleted in the same commit; no adapter bytes change. The card's paper-adapter table and MANIFEST.md use the new paths, and MANIFEST.md records the rename and the last revision with the old names (c53766c4).

Why: the condition-3-zh-5k data config added in the data repo's PR #15 makes the next condition-3 training run upload as condition-3-zh-5k-seed456. Under the old names the evaluation template would not find it, and both earlier condition-3 seeds needed a manual rename (#8, #17).

Merge together with the matching research repo change to the evaluation notebook's condition-3 template, and only after the condition-3 seed-123 evaluation has finished, since that run loads the adapter from the old path.

rename: condition-3 adapter folders to condition-3-zh-5k-seed{42,123}067486ff

madiedgar changed pull request status to merged 10 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment