TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16 download history
TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16 is a 1.8B-parameter feature extraction model by TiGa-RCE. In the last 30 days it was downloaded 33 times (12 in the last 7 days), and 109 times in total.
It ranks #301,199 on the Hub by monthly downloads and #4,399 among feature extraction models.
It has 0 likes.
It is a fine-tune of Alibaba-NLP/gte-Qwen2-1.5B-instruct.
9 models build on gte-Qwen2-1.5B-instruct-MLX-BF16: 9 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 170 times in the last 30 days. See the gte-Qwen2-1.5B-instruct-MLX-BF16 galaxy.
Most downloaded derivatives
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q4 (quantized), 24 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ8 (quantized), 20 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ6 (quantized), 17 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ6e (quantized), 15 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ4e (quantized), 14 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q6 (quantized), 13 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-Q8 (quantized), 13 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ4 (quantized), 11 downloads in 30 days
- TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-oQ8e (quantized), 10 downloads in 30 days
Open TiGa-RCE/gte-Qwen2-1.5B-instruct-MLX-BF16 on Hugging Face