Instructions to use legesher/language-decoded-lora-condition-2-es-5k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use legesher/language-decoded-lora-condition-2-es-5k with Transformers:

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

pipe = pipeline("text-generation", model="legesher/language-decoded-lora-condition-2-es-5k")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("legesher/language-decoded-lora-condition-2-es-5k", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use legesher/language-decoded-lora-condition-2-es-5k 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-condition-2-es-5k"
# 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-condition-2-es-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/legesher/language-decoded-lora-condition-2-es-5k

SGLang

How to use legesher/language-decoded-lora-condition-2-es-5k 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-condition-2-es-5k" \
    --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-condition-2-es-5k",
		"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-condition-2-es-5k" \
        --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-condition-2-es-5k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use legesher/language-decoded-lora-condition-2-es-5k 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-condition-2-es-5k 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-condition-2-es-5k 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-condition-2-es-5k 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-condition-2-es-5k",
    max_seq_length=2048,
)

Docker Model Runner
How to use legesher/language-decoded-lora-condition-2-es-5k with Docker Model Runner:
```
docker model run hf.co/legesher/language-decoded-lora-condition-2-es-5k
```

Language Decoded LoRA — Condition 2: Spanish Keyword-Swapped Code

Spanish keyword-swapped Python via Legesher v0.7.3 (5k subset). Tests whether the language of code keywords matters for reasoning benefits.

Part of the Language Decoded project (Cohere's Tiny Aya Expedition).

For full experiment details, see the Language Decoded LoRA hub.

Training Data

legesher/language-decoded-data / condition-2-es-5k

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-base")
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-base")
model = PeftModel.from_pretrained(base_model, "legesher/language-decoded-lora-condition-2-es-5k")

Citation

@misc{language-decoded-2026,
  title={Language Decoded: Investigating Language-Dependent vs. Structure-Dependent Reasoning Benefits of Code},
  author={Madison Edgar and Saad Ahmed Bazaz and Tom Sherborne and Rashik Shahjahan and Khojasteh Mirza and Sarah Jawaid and Rafay Mustafa and Sohaib Ahmed Bazaz},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/legesher/language-decoded-lora}
}

License

Apache 2.0

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for legesher/language-decoded-lora-condition-2-es-5k

Base model

CohereLabs/tiny-aya-base

Adapter

(8)

this model