metadata
license: mit
base_model: nikhilchandak/OpenForecaster-8B
tags:
- forecasting
- reasoning
- question-answering
- reinforcement-learning
- calibration
- mlx
datasets:
- nikhilchandak/OpenForesight
language:
- en
library_name: mlx
pipeline_tag: text-generation
leonsarmiento/OpenForecaster-8B-8bit-mlx
This model leonsarmiento/OpenForecaster-8B-8bit-mlx was converted to MLX format from nikhilchandak/OpenForecaster-8B using mlx-lm version 0.29.0.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("leonsarmiento/OpenForecaster-8B-8bit-mlx")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)