mindchain
/

haddock_reward_mini

Model card Files Files and versions

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Quantized Reward Model

Original model: Skywork/Skywork-Reward-Llama-3.1-8B-v0.2
Quantization: Q4_K_M
Format: GGUF
Size: ~4.6GB

Downloads last month: 4

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

Log In to view the estimation

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Collection including mindchain/haddock_reward_mini

Trained

Custom-trained models by mindchain: reward models & SAEs. Haddock Reward Mini (8B), function-specific SAEs. AI interpretability & alignment research. • 3 items • Updated about 19 hours ago