FOXAI SEARCH
전체 검색
AI 모델 84767
- gemma-3-27b-it-AWQ-INT4↗
pytorch
Calibrated with 30 samples of `mmlu_philosophy`, got eval accuracy of 80.06, while gemma-3-27b-it-INT4 is 77.17, and bfloat16 baseline is 79.42 Note: please use `VLLM_DISABLE_COMPILE_CACHE=1` to disable compile cache when running this code, e.g. `VLLM_DISABLE_COMPILE_CACHE=1 python example.py`, since there are some issues with the composability of compile in vLLM and torchao, this is expected be resolved in pytorch 2.8. We rely on lm-evaluation-harness to evaluate the quality of the quantized model. Here we only run on mmlu for sanity check.
- Llama-3-8B-Ultrachat-200K-GGUF↗
QuantFactory
- lewm-cube↗
quentinll
- scb10x_-_typhoon-7b-gguf↗
RichardErkhov
- L3.1-Dark-Reasoning-Dark-Planet-Hermes-R1-Uncensored-Horror-Imatrix-MAX-8B-GGUF↗
ScottzillaSystems
- polish-gpt2-xl↗
sdadas
- Seed-X-PPO-7B-GPTQ-Int8↗
字节跳动
- Sakura-LNovel-v0.9b-GGUF-IMX-JPZH↗
shing3232
- convnext-base-224_mnist_sgd_batch-size-64_lr-0.01_steps-4000↗
tanganke
- Tracer-High-1.7B↗
tau-emotion-bench
