david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ 5240c0da23c3ac7df244377a6613b38c269cdcf5

AlpinDale 4599c98f99 feat: dynamic image size support for VLMs		6 сар өмнө
..
__init__.py	5be90c3859 Mamba infrastrucuture support (#586)	6 сар өмнө
arctic.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
baichuan.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
bloom.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
chatglm.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
clip.py	4599c98f99 feat: dynamic image size support for VLMs	6 сар өмнө
commandr.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
dbrx.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
decilm.py	56e0b8223c chore: add base class for LoRA-supported models	7 сар өмнө
deepseek.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
deepseek_v2.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
falcon.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
gemma.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
gpt2.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
gpt_bigcode.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
gpt_j.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
gpt_neox.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
interfaces.py	85ef2fe8b1 chore: clean up placeholder symbols	7 сар өмнө
internlm2.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
jais.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
jamba.py	5be90c3859 Mamba infrastrucuture support (#586)	6 сар өмнө
llama.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
llama_embedding.py	50b7c13db0 refactor: attention selector (#552)	7 сар өмнө
llava.py	4599c98f99 feat: dynamic image size support for VLMs	6 сар өмнө
llava_next.py	4599c98f99 feat: dynamic image size support for VLMs	6 сар өмнө
minicpm.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
mixtral.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
mixtral_quant.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
mlp_speculator.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
mpt.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
olmo.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
opt.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
orion.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
phi.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
phi3_small.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
phi3v.py	4599c98f99 feat: dynamic image size support for VLMs	6 сар өмнө
qwen.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
qwen2.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
qwen2_moe.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
stablelm.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
starcoder2.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө
utils.py	4599c98f99 feat: dynamic image size support for VLMs	6 сар өмнө
xverse.py	0f4a9ee77b quantized lm_head (#582)	7 сар өмнө