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
```

language-decoded-lora / MANIFEST.md

madiedgar

rename: condition-3 adapter folders to condition-3-zh-5k-seed{42,123} (#23)

0d809e5 10 days ago

preview code

Raw History Blame Contribute Delete

3.46 kB

Adapter Manifest — `legesher/language-decoded-lora`

Every trained adapter in this repo, mapped to its project phase and source code corpus. Paper citations should use Phase 3 adapters only. See the README Provenance & Manifest section for the summary.

Generated from the repo file tree; one row per directory containing adapter_config.json.

Phase 3 — paper adapters (`bigcode/the-stack-v2-dedup`, Legesher v0.7.3)

Adapter path	Condition	Seed
`tiny-aya-base/condition-1-en-20k-seed42/`	1	42
`tiny-aya-base/condition-1-en-20k-seed123/`	1	123
`tiny-aya-base/condition-1-en-5k-seed123/`	1	123
`tiny-aya-base/condition-1-en-5k-seed42/`	1	42
`tiny-aya-base/condition-1-en-5k-seed456/`	1	456
`tiny-aya-base/condition-2-es-20k-seed42/`	2	42
`tiny-aya-base/condition-2-es-20k-seed123/`	2	123
`tiny-aya-base/condition-2-es-5k-seed123/`	2	123
`tiny-aya-base/condition-2-es-5k-seed42/`	2	42
`tiny-aya-base/condition-2-es-5k-seed456/`	2	456
`tiny-aya-base/condition-2-ur-20k-seed42/`	2	42
`tiny-aya-base/condition-2-ur-20k-seed123/`	2	123
`tiny-aya-base/condition-2-ur-5k-seed123/`	2	123
`tiny-aya-base/condition-2-ur-5k-seed42/`	2	42
`tiny-aya-base/condition-2-ur-5k-seed456/`	2	456
`tiny-aya-base/condition-2-zh-20k-seed42/`	2	42
`tiny-aya-base/condition-2-zh-20k-seed123/`	2	123
`tiny-aya-base/condition-2-zh-5k-seed123/`	2	123
`tiny-aya-base/condition-2-zh-5k-seed42/`	2	42
`tiny-aya-base/condition-2-zh-5k-seed456/`	2	456
`tiny-aya-base/condition-3-zh-5k-seed42/`	3	42
`tiny-aya-base/condition-3-zh-5k-seed123/`	3	123
`tiny-aya-base/condition-5-es-5k-c4ai-aya-expanse-32b-seed42/`	5	42
`tiny-aya-base/condition-5-es-5k-c4ai-aya-expanse-32b-seed123/`	5	123
`tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed42/`	5	42
`tiny-aya-base/condition-5-ur-5k-c4ai-aya-expanse-32b-seed123/`	5	123
`tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed42/`	5	42
`tiny-aya-base/condition-5-zh-5k-c4ai-aya-expanse-32b-seed123/`	5	123

Folder naming. Each folder is {data config}-seed{seed}, the name the training notebook uploads under. The condition-3 folders were named condition-3-zh-5k-native-code-seed{42,123} until 2026-10-18; the files are unchanged, and the last revision with the old names is c53766c4. Both condition-3 adapters were trained under the data config phase-2-the-stack-v1-condition-3-zh-5k (the condition_name in their training_metrics.json), which reads the same files as the condition-3-zh-5k config.

Phase 2 — preliminary adapters (`bigcode/the-stack` v1, Legesher v0.5.1 / v0.6.0)

Retained for reproducibility of the March-2026 hackathon results. Not cited in the paper. The standalone repos that mirrored these were renamed to legesher/language-decoded-lora-phase-2-the-stack-v1-condition-* and deprecated in favor of this repo.

Adapter path	Condition	Tier
`condition-1-en-32k/`	1	32k
`condition-1-en-5k/`	1	5k
`condition-2-es-5k/`	2	5k
`condition-2-ur-5k/`	2	5k
`condition-2-zh-5k/`	2	5k
`condition-3-zh-5k/`	3	5k

Adapter Manifest — legesher/language-decoded-lora

Phase 3 — paper adapters (bigcode/the-stack-v2-dedup, Legesher v0.7.3)

Phase 2 — preliminary adapters (bigcode/the-stack v1, Legesher v0.5.1 / v0.6.0)

Adapter Manifest — `legesher/language-decoded-lora`

Phase 3 — paper adapters (`bigcode/the-stack-v2-dedup`, Legesher v0.7.3)

Phase 2 — preliminary adapters (`bigcode/the-stack` v1, Legesher v0.5.1 / v0.6.0)