Text Generation
Transformers
Safetensors
lora
aya
tiny-aya
multilingual
code
legesher
tiny-aya-expedition
language-decoded
unsloth
arxiv:2603.11510
arxiv:2211.15533
arxiv:2510.09591
arxiv:1809.05053
arxiv:2308.16884
arxiv:2106.06937
arxiv:2210.03057
Instructions to use legesher/language-decoded-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Commit History
-
rename: correct cond-3 data-source label — native-code, not the-stack-v1
Verified signatureThe cond-3 zh-5k adapter was always trained on native code collected from the internet, never on the-stack-v1. The prior path (after dropping the phase-2- prefix) carried a mislabel inherited from earlier filenames. Rename to the correct data-source suffix: ``` tiny-aya-base/condition-3-zh-5k-the-stack-v1-seed42 → tiny-aya-base/condition-3-zh-5k-native-code-seed42 ``` Pattern matches the cond-5 convention: `condition-N-lang-Nk-<datasource>-seed{N}`. Server-side rename via Copy + Delete operations; LFS object unchanged.8d31336 -
rename: drop "phase-2-" prefix on cond-3 adapter, match cond-5 naming
Madison (Pfaff) EdgarUnverified signatureRename tiny-aya-base/phase-2-the-stack-v1-condition-3-zh-5k-seed42 → tiny-aya-base/condition-3-zh-5k-the-stack-v1-seed42 Reorders the path to match the cond-5 convention (condition-N-lang-Nk-<datasource>-seed{N}). The phase-2-ness is no longer encoded in the path — the-stack-v1 data-source suffix is what distinguishes this adapter from any future phase-3 cond-3 trained on a different data source. Pure git rename; LFS objects unchanged. Signed-off-by: Madison (Pfaff) Edgar <7844510+madiedgar@users.noreply.github.com>672dea2
-
Upload folder using huggingface_hub
Verified signature7d1ac71 -
Upload folder using huggingface_hub
Verified signature1c9b9c0 -
Upload folder using huggingface_hub
Verified signature4ed4206 -
Upload folder using huggingface_hub
Verified signature8c2fe48 -
Upload folder using huggingface_hub
Verified signaturec44c44d -
Upload folder using huggingface_hub
Verified signature971a445 -
Upload folder using huggingface_hub
Verified signature40a615d -
Upload folder using huggingface_hub
Verified signatureb87d13e -
Upload folder using huggingface_hub
Verified signature76e05a3
-
Upload folder using huggingface_hub
Verified signatured36a071 -
Upload folder using huggingface_hub
Verified signaturee537bdb -
Upload folder using huggingface_hub
Verified signature0b1abf7 -
Upload folder using huggingface_hub
Verified signatureb2e949f
-
Upload folder using huggingface_hub
Verified signature9138649 -
Upload folder using huggingface_hub
Verified signaturebbe1912 -
Upload 20 files
Verified signatureb7e2234 -
Upload 21 files
Verified signaturea50c442 -
Upload 20 files
Verified signature4c68f16 -
Upload folder using huggingface_hub
Verified signatured76d67e -
Upload folder using huggingface_hub
Verified signature1cbb139 -
Upload folder using huggingface_hub
Verified signaturec04dd73 -
Upload folder using huggingface_hub
Verified signaturebc062a6 -
Upload folder using huggingface_hub
Verified signaturea48844b -
Upload folder using huggingface_hub
Verified signaturea73a083
-
docs: add condition-1-en-32k to Model Structure table (#7)
- docs: add condition-1-en-32k to Model Structure table (d2d4b8e3fbf29ab8a69717c997f43597dc05b3f3)6ac3acd -
chore: move root adapter to condition-1-en-32k/ subdirectory (#6)
- chore: move root adapter to condition-1-en-32k/ subdirectory (f1dd017c6177852fc48ac41dacfa8ecac028e12c)e4ca1d0 -
docs: fix CITATION.cff url to match repo, set correct type (#5)
- docs: fix CITATION.cff url to match repo, set correct type (8cc2804745ddca35b7b589a7097725a0aad71881)dddcb1a -
feat: consolidate all condition adapters into hub repo subdirectories (#4)
- feat: consolidate all condition adapters into hub repo subdirectories (e669ee8fcee93de9ec766706d595e4d2a8739cb1)0a09c3f -
docs: fix license to Apache 2.0, add hyperparameters + limitations, update citations (#3)
- docs: fix license to Apache 2.0, add hyperparameters + limitations, update citations (52c78860fd325c1f14657b96be34609c1d835ea4)689d1ea
-
Upload adapter_model.safetensors
Verified signatureThis adapter might have gotten updated by mistake, I am replacing it with the backup I had downloaded in my pc57a2134 -
Upload model trained with Unsloth
Verified signatureUpload model trained with Unsloth 2x faster12c83fb
-
Upload model trained with Unsloth
Verified signatureUpload model trained with Unsloth 2x fasterb7ab8ee
-
Update model card: fix conditions, base model, benchmarks, languages (#1)
- Update model card: fix conditions, base model, benchmarks, languages (bf55f60c10d5d40de2f0c7a6653c7e707beef94c)e4f13e7
-
init: create README.md
Verified signaturef48842c
-
initial commit
Verified signatureb51e5c6