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 9 days ago

base: refs/heads/main

←

from: refs/pr/23

Discussion Files changed

-3

madiedgar

Legesher org 9 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 9 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