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")

# 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 Studio

How to use legesher/language-decoded-lora with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for legesher/language-decoded-lora to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for legesher/language-decoded-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for legesher/language-decoded-lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="legesher/language-decoded-lora",
    max_seq_length=2048,
)

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

Add Attribution & takedown section

#13

by madiedgar - opened 17 days ago

base: refs/heads/main

←

from: refs/pr/13

Discussion Files changed

+32

-2

Files changed (1) hide show

README.md +32 -2

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ The hypothesis is **not** that non-English code matches or exceeds English code
 ## Base Model
-All adapters are trained on [CohereLabs/tiny-aya-base](https://huggingface.co/CohereLabs/tiny-aya-base) (3.35B parameters). Tiny Aya was chosen because it is small (deployable on a single 16 GB T4 GPU via QLoRA), accessible (Apache 2.0-licensed), and supports 70+ languages with explicit emphasis on lower-resourced ones — which makes the experimental ladder viable for `ur` at all.
 ## Adapter Inventory
@@ -222,4 +222,34 @@ Paper-grade evaluation results live on [`legesher/language-decoded-experiments`]
 ## License
-Apache 2.0

 ## Base Model
+All adapters are trained on [CohereLabs/tiny-aya-base](https://huggingface.co/CohereLabs/tiny-aya-base) (3.35B parameters). Tiny Aya was chosen because it is small (deployable on a single 16 GB T4 GPU via QLoRA), openly available (released under CC-BY-NC-4.0), and supports 70+ languages with explicit emphasis on lower-resourced ones — which makes the experimental ladder viable for `ur` at all.
 ## Adapter Inventory
 ## License
+CC-BY-NC-4.0. The adapters inherit the license of the base model,
+[CohereLabs/tiny-aya-base](https://huggingface.co/CohereLabs/tiny-aya-base)
+(CC-BY-NC-4.0). The training datasets
+([legesher/language-decoded-data](https://huggingface.co/datasets/legesher/language-decoded-data))
+are separately licensed under Apache-2.0.
+## Provenance, attribution & takedown
+These adapters were fine-tuned from
+[`CohereLabs/tiny-aya-base`](https://huggingface.co/CohereLabs/tiny-aya-base)
+on a specific revision of the
+[`legesher/language-decoded-data`](https://huggingface.co/datasets/legesher/language-decoded-data)
+training conditions (see each adapter's configuration for the
+condition and revision).
+If you are the author of source code included in the training data
+and would like attribution added or your code removed, open a
+discussion on the dataset repository's **Community** tab or email
+**support@legesher.com**. Removals are propagated in a new dataset
+revision. Adapters already trained are frozen historical artifacts:
+a dataset removal does not alter existing adapter weights, but we
+will note affected conditions here and take reported concerns about
+specific adapters into account.
+**Usage caution.** These are research artifacts, not
+production-ready models. Documented side effects include code
+fragments leaking into natural-language output (strongest for Urdu
+adapters) and matched-language regressions on specific evaluation
+cells; the Condition 5 adapters were trained on corpora containing
+raw translator output. Evaluate per language and per task before any
+downstream use.