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
```

docs: drop the submitted-paper-title banner

#19

by madiedgar - opened 15 days ago

base: refs/heads/main

←

from: refs/pr/19

Discussion Files changed

-3

Files changed (1) hide show

README.md +1 -3

README.md CHANGED Viewed

@@ -33,8 +33,6 @@ pipeline_tag: text-generation
 QLoRA adapters fine-tuned on multilingual code conditions for the **Language Decoded** project (part of [Cohere's Tiny Aya Expedition](https://aya.for.ai)).
-> **Submitted paper title (2026-05-26):** _Language, Decoded: Exploring the Impact of Fine-Tuning a Multilingual Model on Native-Language Code_
 ## ⚠️ Phase 3 eval numbers — read the experiments repo before citing
 Original Phase 3 `_summary_*.json` files on [`legesher/language-decoded-experiments`](https://huggingface.co/datasets/legesher/language-decoded-experiments) **under-report cond-5 SIB-200 accuracy by 20–35pp** because the strict inference-time extractor refused native-script answers. Cite the `_summary_reparsed_*.json` siblings (refined extractor) instead. **Five** Phase 3 SIB-200 conclusions also flip win→loss against baseline once the extractor is corrected (`cond-2-es-5k`, `cond-2-es-20k`, `cond-2-ur-20k`, `cond-2-zh-20k`, `cond-3-zh-5k`), and `cond-2-ur-5k`'s gain deflates 4.4×. See the [banner on the experiments repo](https://huggingface.co/datasets/legesher/language-decoded-experiments) (top of the README) for the full picture.
@@ -53,7 +51,7 @@ All adapters are trained on [CohereLabs/tiny-aya-base](https://huggingface.co/Co
 This repo holds adapters from **two generations of the project**, kept side by side and clearly separated by folder. See the [Provenance & Manifest](#provenance--manifest) section for a complete path → phase → source-corpus map, and [`MANIFEST.md`](MANIFEST.md) for the machine-readable version.
-- **Paper adapters (Phase 3 · The Stack v2-dedup)** — live under the **`tiny-aya-base/`** prefix. These are the adapters cited in the submitted paper; cond-1, cond-2, and cond-5 were re-trained from scratch on the cleaner [`bigcode/the-stack-v2-dedup`](https://huggingface.co/datasets/bigcode/the-stack-v2-dedup) corpus.
 - **Preliminary adapters (Phase 2 · The Stack v1)** — live as **flat top-level folders** (`condition-1-en-32k/`, `condition-2-zh-5k/`, …). These are the original March-2026 hackathon adapters trained on [`bigcode/the-stack`](https://huggingface.co/datasets/bigcode/the-stack) (v1, non-dedup), retained for reproducibility. **Do not cite these for the paper.**
 ### Paper adapters — Phase 3 · The Stack v2-dedup

 QLoRA adapters fine-tuned on multilingual code conditions for the **Language Decoded** project (part of [Cohere's Tiny Aya Expedition](https://aya.for.ai)).
 ## ⚠️ Phase 3 eval numbers — read the experiments repo before citing
 Original Phase 3 `_summary_*.json` files on [`legesher/language-decoded-experiments`](https://huggingface.co/datasets/legesher/language-decoded-experiments) **under-report cond-5 SIB-200 accuracy by 20–35pp** because the strict inference-time extractor refused native-script answers. Cite the `_summary_reparsed_*.json` siblings (refined extractor) instead. **Five** Phase 3 SIB-200 conclusions also flip win→loss against baseline once the extractor is corrected (`cond-2-es-5k`, `cond-2-es-20k`, `cond-2-ur-20k`, `cond-2-zh-20k`, `cond-3-zh-5k`), and `cond-2-ur-5k`'s gain deflates 4.4×. See the [banner on the experiments repo](https://huggingface.co/datasets/legesher/language-decoded-experiments) (top of the README) for the full picture.
 This repo holds adapters from **two generations of the project**, kept side by side and clearly separated by folder. See the [Provenance & Manifest](#provenance--manifest) section for a complete path → phase → source-corpus map, and [`MANIFEST.md`](MANIFEST.md) for the machine-readable version.
+- **Paper adapters (Phase 3 · The Stack v2-dedup)** — live under the **`tiny-aya-base/`** prefix. These are the adapters cited in the paper; cond-1, cond-2, and cond-5 were re-trained from scratch on the cleaner [`bigcode/the-stack-v2-dedup`](https://huggingface.co/datasets/bigcode/the-stack-v2-dedup) corpus.
 - **Preliminary adapters (Phase 2 · The Stack v1)** — live as **flat top-level folders** (`condition-1-en-32k/`, `condition-2-zh-5k/`, …). These are the original March-2026 hackathon adapters trained on [`bigcode/the-stack`](https://huggingface.co/datasets/bigcode/the-stack) (v1, non-dedup), retained for reproducibility. **Do not cite these for the paper.**
 ### Paper adapters — Phase 3 · The Stack v2-dedup