summaryrefslogtreecommitdiff
path: root/convert.py
AgeCommit message (Expand)Author
2024-05-16convert : get general.name from model dir, not its parent (#5615)Jared Van Bortel
2024-05-13convert.py: Outfile default name change and additional metadata support (#4858)Brian
2024-05-08convert-hf : save memory with lazy evaluation (#7075)compilade
2024-05-08convert.py : --vocab-only generates false but valid params (#7027)20kdc
2024-05-03convert.py : add python logging instead of print() (#6511)Brian
2024-04-21llama : support Llama 3 HF conversion (#6745)Pedro Cuenca
2024-04-10convert.py : add consolidated.safetensors for mixtral 8x22b (#6587)slaren
2024-04-09BERT tokenizer fixes (#6498)Jared Van Bortel
2024-04-08Comment explaining a decision (#6531)kunnis
2024-04-03ggml : mul_mat_id use the same tensor for all the experts (#6387)slaren
2024-03-28convert : refactor vocab selection logic (#6355)Jared Van Bortel
2024-03-18convert : use f32 outtype for bf16 tensors (#6106)Romain D
2024-03-14llama : support models without vocabulary (#5798)Michael Podvitskiy
2024-03-06convert : remove AWQ remnants (#5768)Georgi Gerganov
2024-03-02convert : automatically fall back to HfVocab if tokenizer.model doesn't exist...Jared Van Bortel
2024-02-14llava : support v1.6 (#5267)John
2024-02-06convert : fix TypeError on GPT-2 vocab.json (#5288)Sang-Kil Park
2024-02-06py : handle byte tokens in `get_token_type` (#5341)Georgi Gerganov
2024-01-29py : fix except (#5194)Georgi Gerganov
2024-01-29py : improve BPE tokenizer support (#5189)Sang-Kil Park
2024-01-20convert : partially revert PR #4818 (#5041)Jared Van Bortel
2024-01-18convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#5019)David Sommers
2024-01-17py : fix whitespaceGeorgi Gerganov
2024-01-17py : fix missing added_tokens_dict for SPM and BPE vocabs (#4971)Georgi Gerganov
2024-01-09convert.py : fix vanilla LLaMA model conversion (#4818)Austin
2023-12-27llama : add AWQ for llama, llama2, mpt, and mistral models (#4593)Nam D. Tran
2023-12-27Add byte token type when tokenizer.model is not exists (#4641)wonjun Jang
2023-12-14convert : support loading vocab from fast tokenizer config (#3633)wonjun Jang
2023-12-13llama : add Mixtral support (#4406)slaren
2023-12-12english : use `typos` to fix comments and logs (#4354)Richard Kiss
2023-11-30convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#4258)slaren
2023-11-25Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#4189)crasm
2023-11-20ci : add flake8 to github actions (python linting) (#4129)Galunid
2023-11-17convert : use 'model' value if it exists. This allows karpathy/tinyllamas to ...Don Mahurin
2023-11-13convert.py: also look for plain model.safetensors (#4043)afrideva
2023-11-11gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)Kerfuffle
2023-11-09scripts: Generalize convert scripts (#3838)Galunid
2023-11-01llama : implement YaRN RoPE scaling (#2268)cebtenzzre
2023-10-28convert : ignore tokens if their IDs are within [0, vocab_size) (#3831)Georgi Gerganov
2023-10-22llama : validate special token ids are in range when loading GGUF model (#3635)Kerfuffle
2023-10-20gguf : support big endian platform (#3552)Qin Yue Chen
2023-10-03Work on the BPE tokenizer (#3252)goerch
2023-10-02gguf : general usability improvements (#3409)cebtenzzre
2023-09-27convert : remove bug in convert.py permute function (#3364)Zhang Peiyuan
2023-09-10convert: remove most of the n_mult usage in convert.py (#3098)Erik Scholz
2023-09-07convert : fix F32 ftype not being saved (#3048)Cebtenzzre
2023-09-05convert: fix convert.py not working with int filename_stem (#3028)Erik Scholz
2023-09-03convert.py : BPE fixes (#2938)Kerfuffle
2023-08-31convert : fix another python 3.8 issue (#2949)Cebtenzzre
2023-08-31scripts: Use local gguf package when running from repo (#2927)Kerfuffle
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-04 21:30:58 +0000