Kerfuffle
e06cbcee73
gguf : add Python script to convert GGMLv3 LLaMA models to GGUF ( #2682 )
...
* First pass at converting GGMLv3 LLaMA models to GGUF
* Cleanups, better output during conversion
* Fix vocab space conversion logic
* More vocab conversion fixes
* Add description to converted GGUF files
* Improve help text, expand warning
* Allow specifying name and description for output GGUF
* Allow overriding vocab and hyperparams from original model metadata
* Use correct params override var name
* Fix wrong type size for Q8_K
Better handling of original style metadata
* Set default value for gguf add_tensor raw_shape KW arg
2023-08-21 17:45:52 +03:00
klosax
6a69a693cb
gguf.py : fix rope scale kv
2023-08-21 13:23:10 +02:00
klosax
bd5a57901b
gguf.py : fix for falcon 40b
2023-08-19 01:01:52 +02:00
klosax
147a99bd3a
gguf.py : reverse GGUF_MAGIC
2023-08-17 23:24:04 +02:00
klosax
640ddc4259
gguf.py : gptneox mapping
2023-08-17 21:43:10 +02:00
M. Yusuf Sarıgöz
fc3a523211
gguf.py : write tensors in a single pass ( #2644 )
...
* gguf : single pass for writing tensors + refactoring writer
* gguf : single pass for writing tensors + refactoring writer
* gguf : single pass for writing tensors + refactoring writer
* gguf : style fixes in simple conversion script
* gguf : refactor gptneox conversion script
* gguf : rename h5 to hf (for HuggingFace)
* gguf : refactor pth to gguf conversion script
* gguf : rm file_type key and method
* gguf.py : fix vertical alignment
* gguf.py : indentation
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-08-17 21:57:39 +03:00
Georgi Gerganov
acaa98234a
convert.py : fix HF tensor permuting / unpacking
...
ggml-ci
2023-08-17 21:06:45 +03:00
Georgi Gerganov
e0429d38e4
convert-new.py : output gguf ( #2635 )
...
* convert-new.py : output gguf (WIP)
* convert-new.py : add gguf key-value pairs
* llama : add hparams.ctx_train + no longer print ftype
* convert-new.py : minor fixes
* convert-new.py : vocab-only option should work now
* llama : fix tokenizer to use llama_char_to_byte
* tests : add new ggml-vocab-llama.gguf
* convert-new.py : tensor name mapping
* convert-new.py : add map for skipping tensor serialization
* convert-new.py : convert script now works
* gguf.py : pick some of the refactoring from #2644
* convert-new.py : minor fixes
2023-08-17 17:19:52 +03:00
Georgi Gerganov
c8ee87f141
gguf.py : merge all files in gguf.py
2023-08-16 19:55:49 +03:00
klosax
b6056c3db8
gguf.py : add tensor data layout
2023-08-15 19:53:44 +02:00
klosax
cedb4870c6
gguf.py : add token types
2023-08-14 22:08:40 +02:00
Georgi Gerganov
62490f1380
gguf : use UNIX line ending
2023-08-14 13:04:35 +03:00
klosax
5c5a95ba2d
gguf.py : dont add empty strings
2023-08-14 11:22:06 +02:00
M. Yusuf Sarıgöz
91d4bfd536
convert : write more metadata for LLaMA
2023-08-13 13:29:46 +03:00
klosax
d2ce9cfe8d
gguf.py : n_layer --> n_block
2023-08-13 00:01:20 +02:00
klosax
5d81a715d4
gguf.py : no need to convert tensors twice
2023-08-12 21:45:45 +02:00
klosax
4357e692ac
gguf.py : use custom alignment if present
2023-08-07 13:51:26 +02:00
klosax
278ada9572
gguf.py : bytesarray for gpt2bpe tokenizer
2023-08-04 04:07:57 +02:00
klosax
49380a23a3
gguf.py : accumulate kv and tensor info data + special tokens
2023-08-01 23:37:48 +02:00
M. Yusuf Sarıgöz
7aa0a0e7f7
gguf : support custom alignment value
2023-07-31 09:59:36 +03:00
klosax
ccd81a751b
gguf.py : add layer norm eps and merges
2023-07-30 14:48:14 +02:00
M. Yusuf Sarıgöz
32e037ffbe
gguf : fix set is not subscriptable
2023-07-30 01:01:13 +03:00
klosax
9577821487
gguf.py : support any type
2023-07-29 21:29:07 +02:00
M. Yusuf Sarıgöz
0f5e57f01d
gguf : handle already encoded string
2023-07-29 19:56:06 +03:00
M. Yusuf Sarıgöz
cc3dd7f042
gguf : write tokenizer data
2023-07-29 13:30:22 +03:00
M. Yusuf Sarıgöz
8a76dd8a85
gguf : write tensors one by one
2023-07-29 13:17:28 +03:00
M. Yusuf Sarıgöz
c861e234f4
gguf : write tensors one by one
2023-07-29 12:49:01 +03:00
M. Yusuf Sarıgöz
0c219fb5b5
gguf : fix writing gguf arrays
2023-07-29 12:42:54 +03:00
M. Yusuf Sarıgöz
93f7f7aef7
gguf : write tensors one by one and code reuse
2023-07-29 12:34:35 +03:00
M. Yusuf Sarıgöz
ea5f9ad2ca
gguf : fix writing gguf arrays
2023-07-29 12:25:43 +03:00
M. Yusuf Sarıgöz
06f423a8e1
gguf : write sample tensors to read
2023-07-29 10:26:26 +03:00
M. Yusuf Sarıgöz
1495735aac
gguf : fix writing tensors
2023-07-29 00:26:22 +03:00
M. Yusuf Sarıgöz
11ef380c2a
GGUF : write tensor ( #2426 )
...
* WIP: Write tensor
* GGUF : Support writing tensors in Python
* refactor : rm unused import and upd todos
* fix : fix errors upd writing example
* rm example.gguf
* gitignore *.gguf
* undo formatting
2023-07-28 11:34:16 +03:00
Georgi Gerganov
158be8f7f4
gguf.py : some code style changes
2023-07-27 15:37:06 +03:00
M. Yusuf Sarıgöz
c85d3178b3
refactor : reduce code duplication and better API ( #2415 )
2023-07-27 10:29:29 +03:00
M. Yusuf Sarıgöz
bae6b125f6
wip : implement GGUF ( #2397 )
...
* Add LLAMA_DEFAULT_RMS_EPS so we can change the default (#2384 )
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* WIP: python class to write GGUF, incomplete C apı for reading
---------
Co-authored-by: Kawrakow <48489457+ikawrakow@users.noreply.github.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2023-07-26 18:21:13 +03:00
