Awni Hannun 5cae0a60e6 deepseek v3 model with pipeline parallelism (#1191) ... * deepseekv3 * use upload_large_file instead of deprecated multi comit * add pipeline generation and example * comment * get fp16 working * use mlx==0.22		2025-01-09 15:55:53 -08:00
..
chat.py	fix encoding with special tokens + chat template (#1189)	2025-01-03 10:50:59 -08:00
generate_response.py	fix encoding with special tokens + chat template (#1189)	2025-01-03 10:50:59 -08:00
lora_config.yaml	Update lora_config.yaml with new param: num_layers (#1068)	2024-10-26 09:34:46 -07:00
merge_config.yaml	Support for slerp merging models (#455)	2024-02-19 20:37:15 -08:00
pipeline_generate.py	deepseek v3 model with pipeline parallelism (#1191)	2025-01-09 15:55:53 -08:00