Stanisław Szymczyk b50c07c247 Added five new DeepSeek-V2-specific parameters: ... - leading_dense_block_count => hparams.n_leading_dense_layer, - expert_feed_forward_length => hparams.n_expert_ff, - expert_shared_count => hparams.n_expert_shared, - attention.q_lora_rank => hparams.n_lora_q, - attention.kv_lora_rank => hparams.n_lora_kv		2024-05-18 14:40:09 +02:00
..
__init__.py	convert-hf : support direct Q8_0 conversion (#7234)	2024-05-13 14:10:51 -04:00
constants.py	Added five new DeepSeek-V2-specific parameters:	2024-05-18 14:40:09 +02:00
gguf.py	gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2023-11-11 08:04:50 +03:00
gguf_reader.py	convert-hf : save memory with lazy evaluation (#7075)	2024-05-08 18:16:38 -04:00
gguf_writer.py	Added five new DeepSeek-V2-specific parameters:	2024-05-18 14:40:09 +02:00
lazy.py	convert-hf : support direct Q8_0 conversion (#7234)	2024-05-13 14:10:51 -04:00
py.typed	convert : various script cleanups/fixes + merges and special token handling (#2842)	2023-08-30 11:25:50 +03:00
quants.py	convert-hf : support direct Q8_0 conversion (#7234)	2024-05-13 14:10:51 -04:00
tensor_mapping.py	Added initial support for DeepseekV2ForCausalLM.	2024-05-16 20:16:35 +02:00
vocab.py	convert-hf : save memory with lazy evaluation (#7075)	2024-05-08 18:16:38 -04:00