Instructions to use altbrainblock/tiny_med_es with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use altbrainblock/tiny_med_es with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("altbrainblock/tiny_med_es", dtype="auto") - llama-cpp-python
How to use altbrainblock/tiny_med_es with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="altbrainblock/tiny_med_es", filename="tiny_med_es-unsloth.F16.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use altbrainblock/tiny_med_es with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf altbrainblock/tiny_med_es:Q4_K_M # Run inference directly in the terminal: llama-cli -hf altbrainblock/tiny_med_es:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf altbrainblock/tiny_med_es:Q4_K_M # Run inference directly in the terminal: llama-cli -hf altbrainblock/tiny_med_es:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf altbrainblock/tiny_med_es:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf altbrainblock/tiny_med_es:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf altbrainblock/tiny_med_es:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf altbrainblock/tiny_med_es:Q4_K_M
Use Docker
docker model run hf.co/altbrainblock/tiny_med_es:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use altbrainblock/tiny_med_es with Ollama:
ollama run hf.co/altbrainblock/tiny_med_es:Q4_K_M
- Unsloth Studio new
How to use altbrainblock/tiny_med_es 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 altbrainblock/tiny_med_es 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 altbrainblock/tiny_med_es to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for altbrainblock/tiny_med_es to start chatting
- Docker Model Runner
How to use altbrainblock/tiny_med_es with Docker Model Runner:
docker model run hf.co/altbrainblock/tiny_med_es:Q4_K_M
- Lemonade
How to use altbrainblock/tiny_med_es with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull altbrainblock/tiny_med_es:Q4_K_M
Run and chat with the model
lemonade run user.tiny_med_es-Q4_K_M
List all available models
lemonade list
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 altbrainblock/tiny_med_es to start chattingUsing HuggingFace Spaces for Unsloth
# No setup required# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for altbrainblock/tiny_med_es to start chattingBaby Med LLM

- Prompt
- baby llm
Spanish Domain Exper LLMs
This project represents an ongoing initiative at Alt aimed at enhancing the Spanish language capabilities of LLMs' base models. By incorporating diverse and rich Spanish corpora, our objective is to improve the model's understanding and generation of specific domain languages.
This effort is part of a broader initiative to adapt and refine large language models (LLMs) for more accurate and nuanced performance across a variety of linguistic contexts, including but not limited to medicine, law, finance, agriculture, construction, and scientific research. By integrating specialized vocabularies and knowledge from these diverse fields into our fine-tuning process, specifically focusing on Spanish corpora, our goal is to significantly enhance the model's proficiency. This comprehensive approach ensures that the 'Mistral7b' model not only excels in general language understanding and generation but also possesses deep expertise in specific domains. Consequently, this enables more effective, natural, and contextually relevant interactions in Spanish, tailored to the unique requirements of professionals across these critical sectors.
- Developed by: altbrainblock
- License: apache-2.0
- Finetuned from model : unsloth/mistral-7b-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 17
4-bit
8-bit
16-bit
Model tree for altbrainblock/tiny_med_es
Base model
unsloth/mistral-7b-bnb-4bit
Install Unsloth Studio (macOS, Linux, WSL)
# Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for altbrainblock/tiny_med_es to start chatting