Instructions to use eldinosaur/cuentas-claras-sat-classifier-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eldinosaur/cuentas-claras-sat-classifier-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="eldinosaur/cuentas-claras-sat-classifier-gguf",
	filename="cuentas-claras-sat-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use eldinosaur/cuentas-claras-sat-classifier-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf eldinosaur/cuentas-claras-sat-classifier-gguf: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 eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf eldinosaur/cuentas-claras-sat-classifier-gguf: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 eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M

Use Docker

docker model run hf.co/eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use eldinosaur/cuentas-claras-sat-classifier-gguf with Ollama:
```
ollama run hf.co/eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
```

Unsloth Studio

How to use eldinosaur/cuentas-claras-sat-classifier-gguf 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 eldinosaur/cuentas-claras-sat-classifier-gguf 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 eldinosaur/cuentas-claras-sat-classifier-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for eldinosaur/cuentas-claras-sat-classifier-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use eldinosaur/cuentas-claras-sat-classifier-gguf with Docker Model Runner:
```
docker model run hf.co/eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M
```

Lemonade

How to use eldinosaur/cuentas-claras-sat-classifier-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull eldinosaur/cuentas-claras-sat-classifier-gguf:Q4_K_M

Run and chat with the model

lemonade run user.cuentas-claras-sat-classifier-gguf-Q4_K_M

List all available models

lemonade list

Cuentas Claras — SAT Transaction Classifier (GGUF)

GGUF quantizations of the fine-tuned MiniCPM4.1-8B SAT transaction classifier, for local inference with llama.cpp (🦙 / 🔌 — no cloud, runs on a laptop).

File	Quant	~Size	Use
`cuentas-claras-sat-Q4_K_M.gguf`	Q4_K_M	~4.9 GB	laptop default
`cuentas-claras-sat-Q8_0.gguf`	Q8_0	~8.5 GB	higher quality

Run

llama-cli -m cuentas-claras-sat-Q4_K_M.gguf --jinja \
  -sys "Eres un clasificador contable mexicano. Responde solo JSON." \
  -p 'Clasifica: "Suscripción anual a Adobe Creative Cloud"'

Returns the SAT account, deductibility and IVA treatment as JSON. See the base model card for training details (eval_loss 0.155, token accuracy 96.1%).

Not tax advice. Account codes/rules are simplified and must be verified vs the SAT catalogue.

Downloads last month: -

GGUF

Model size

8B params

Architecture

minicpm

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for eldinosaur/cuentas-claras-sat-classifier-gguf

Base model

eldinosaur/cuentas-claras-sat-classifier-minicpm

Quantized

(1)

this model

eldinosaur
/

cuentas-claras-sat-classifier-gguf

Cuentas Claras — SAT Transaction Classifier (GGUF)

Run

Model tree for eldinosaur/cuentas-claras-sat-classifier-gguf

Space using eldinosaur/cuentas-claras-sat-classifier-gguf 1