nvidia-Llama-3.1-Nemotron-70B-Reward-HF-AQ41
mlx-community/nvidia-Llama-3.1-Nemotron-70B-Reward-HF-AQ41
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
71B
Weights (est.)
≈ 39.7 GB
Mac memory (est.)
48 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- nvidia/Llama-3.1-Nemotron-70B-Reward-HF (quantized)
- Vendor
- NVIDIA
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- llama3.1
- Downloads
- 39 in the last 30 days · 680 all time · 0 likes
- Published
- 2024-10-02 · updated 2024-10-02 (2y ago)
- Languages
- en
- Tags
- llama, nvidia, llama3.1, reward model