Instructions to use clibrain/lince-zero with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use clibrain/lince-zero with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="clibrain/lince-zero", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("clibrain/lince-zero", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("clibrain/lince-zero", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use clibrain/lince-zero with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "clibrain/lince-zero" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "clibrain/lince-zero", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/clibrain/lince-zero
- SGLang
How to use clibrain/lince-zero 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 "clibrain/lince-zero" \ --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": "clibrain/lince-zero", "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 "clibrain/lince-zero" \ --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": "clibrain/lince-zero", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use clibrain/lince-zero with Docker Model Runner:
docker model run hf.co/clibrain/lince-zero
Commit ·
dd95505
1
Parent(s): f6c197b
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ library_name: transformers
|
|
| 11 |
inference: false
|
| 12 |
---
|
| 13 |
|
| 14 |
-
**LINCE-ZERO** (Llm for Instructions from Natural Corpus en Español) is a
|
| 15 |
|
| 16 |
Developed by [Clibrain](https://www.clibrain.com/), it is a causal decoder-only model with 7B parameters. LINCE-ZERO is based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and has been fine-tuned using an 80k examples proprietary dataset inspired in famous instruction datasets such as Alpaca and Dolly.
|
| 17 |
|
|
@@ -58,7 +58,7 @@ Be one of the first to discover the possibilities of LINCE!
|
|
| 58 |
|
| 59 |
## Model Description
|
| 60 |
|
| 61 |
-
LINCE-ZERO (Llm for Instructions from Natural Corpus en Español) is a
|
| 62 |
|
| 63 |
- **Developed by:** [Clibrain](https://www.clibrain.com/)
|
| 64 |
- **Model type:** Language model, instruction model, causal decoder-only
|
|
|
|
| 11 |
inference: false
|
| 12 |
---
|
| 13 |
|
| 14 |
+
**LINCE-ZERO** (Llm for Instructions from Natural Corpus en Español) is a Spanish instruction-tuned LLM 🔥
|
| 15 |
|
| 16 |
Developed by [Clibrain](https://www.clibrain.com/), it is a causal decoder-only model with 7B parameters. LINCE-ZERO is based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and has been fine-tuned using an 80k examples proprietary dataset inspired in famous instruction datasets such as Alpaca and Dolly.
|
| 17 |
|
|
|
|
| 58 |
|
| 59 |
## Model Description
|
| 60 |
|
| 61 |
+
LINCE-ZERO (Llm for Instructions from Natural Corpus en Español) is a Spanish instruction-tuned large language model. Developed by [Clibrain](https://www.clibrain.com/), it is a causal decoder-only model with 7B parameters. LINCE-ZERO is based on [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) and has been fine-tuned using an 80k examples proprietary dataset.
|
| 62 |
|
| 63 |
- **Developed by:** [Clibrain](https://www.clibrain.com/)
|
| 64 |
- **Model type:** Language model, instruction model, causal decoder-only
|