Text Classification
Safetensors
MLX
English
neural-txt
bert
reward-model
answer-equivalence
question-answering
Instructions to use paperbd/neuraltxt-reward-tiny-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use paperbd/neuraltxt-reward-tiny-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir neuraltxt-reward-tiny-mlx paperbd/neuraltxt-reward-tiny-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
NeuralTxt Reward Model MLX
MLX-ready package for paperbd/neuraltxt-reward-tiny.
This repo contains:
model.safetensors: MiniLM/BERT encoder weights readable by MLX.reward_head.safetensors: clamped linear reward head in MLX safetensors format.- tokenizer files copied from the source reward model.
Usage
from neuraltxt import NeuralTxtReward
reward = NeuralTxtReward(backend="mlx")
score = reward.score(
response="Paris is the capital of France.",
reference="The capital of France is Paris.",
)
To load this repo explicitly:
reward = NeuralTxtReward("paperbd/neuraltxt-reward-tiny-mlx", backend="mlx")
- Downloads last month
- 79
Model size
22.7M params
Tensor type
F32
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for paperbd/neuraltxt-reward-tiny-mlx
Base model
nreimers/MiniLM-L6-H384-uncased Quantized
sentence-transformers/all-MiniLM-L6-v2 Finetuned
paperbd/neuraltxt-reward-tiny