Ștefan-Gabriel Muscalu a94e6ff877

update: support Qwen2-57B-A14B (#7835) ...

* update: convert-hf-to-gguf.py to support Qwen2-57B-A14B

* fix: QWEN2MOE support for expert_feed_forward_length

previously, expert ff was taken from n_ff (intermediate size) but it is now properly taken from LLM_KV_EXPERT_FEED_FORWARD_LENGTH

n_ff_exp and n_ff_shared_exp are now properly calculated

* update: convert-hf-to-gguf.py cleanup for Qwen2MoeForCausalLM

* fix: QWEN2MOE support for expert_feed_forward_length

previously, expert ff was taken from n_ff (intermediate size) but it is now properly taken from LLM_KV_EXPERT_FEED_FORWARD_LENGTH

n_ff_exp and n_ff_shexp are now properly calculated

2024-06-17 21:08:46 +02:00

..

__init__.py

convert-hf : support direct Q8_0 conversion (#7234)

2024-05-13 14:10:51 -04:00

constants.py

update: support Qwen2-57B-A14B (#7835)

2024-06-17 21:08:46 +02:00

gguf_reader.py

gguf-py : fix and simplify quantized shape round-trip (#7483)

2024-05-25 11:11:48 +10:00

gguf_writer.py

update: support Qwen2-57B-A14B (#7835)

2024-06-17 21:08:46 +02:00

gguf.py

gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)

2023-11-11 08:04:50 +03:00

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

gguf-py : fix and simplify quantized shape round-trip (#7483)

2024-05-25 11:11:48 +10:00

tensor_mapping.py

llama : add jina v2 base code (#7596)

2024-06-06 10:22:41 +03:00

vocab.py

Move convert.py to examples/convert-legacy-llama.py (#7430)

2024-05-30 21:40:00 +10:00