05b183fe7b
compatibility fix
2024-06-10 14:00:13 -04:00
854bd64a5d
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 13:55:08 -04:00
b843445827
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 13:54:41 -04:00
efa06098a6
swap bar orders
2024-06-10 07:58:17 -04:00
4550826871
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 07:55:24 -04:00
c1b1a29266
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 07:55:01 -04:00
ad02c9409a
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 07:54:50 -04:00
99f9a24805
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 07:54:18 -04:00
7eea552db8
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-10 07:54:06 -04:00
79bd2bfcb0
catch oversights
2024-06-09 20:22:17 -04:00
f7e7983946
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-09 20:17:25 -04:00
1e2d9cb589
progress bar, fix split logic
2024-06-09 17:31:25 -04:00
70a6bc91cc
Update gguf-py/gguf/gguf_writer.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-09 17:08:11 -04:00
0417104397
fix linting
2024-06-09 16:05:08 -04:00
9d7f694438
fix typing and clean up
2024-06-09 16:02:23 -04:00
f7ecd99691
appease linter
2024-06-09 13:09:05 -04:00
5a96b8f27f
remove SplitStrategy, SplitArguments
2024-06-09 13:08:06 -04:00
0471f67f4f
cleanup round 1
2024-06-09 12:40:02 -04:00
a234bf821b
fix linting
2024-06-09 11:23:55 -04:00
0779f2f74f
tidy up
2024-06-09 11:20:14 -04:00
ba1be979eb
fix ti data messiness
2024-06-09 11:10:33 -04:00
ff2dd7d30d
try to refactor kv data (still fails)
2024-06-09 10:29:47 -04:00
97dd416903
kv/ti data are still wrong
2024-06-09 00:34:36 -04:00
03cc9bcbe8
use simplification from #7827
2024-06-08 23:14:26 -04:00
666bb097a2
Merge branch 'master' into convert-split
2024-06-08 23:06:18 -04:00
282e71fb39
edit cmd line args
2024-06-08 23:00:42 -04:00
ed9f252118
gguf-py : decouple adding metadata from writing in GGUFWriter ( #7827 )
...
Main changes of this PR is to consolidate GGUFWriter.add_key and GGUFWriter.add_val into GGUFWriter.add_key_value.
In addition use_temp_file is now opt-in instead of opt-out defaulting to False.
Also GGUFWriter now does not require output file name until when actually writing to it.
And GGUFWriter doesn't really need to eagerly prepare the data layout of the metadata
2024-06-09 12:34:29 +10:00
02be0dd654
attempt 3 to appease the linter
2024-06-07 21:26:40 -04:00
891b19cb81
attempt 2 to appease the linter
2024-06-07 21:20:46 -04:00
2e70fa1055
attempt to appease the linter
2024-06-07 21:18:30 -04:00
dc5cf5fd82
Update gguf-py/gguf/gguf_writer_split.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-07 17:26:30 -04:00
1312e287ec
Update gguf-py/gguf/constants.py
...
Co-authored-by: compilade <git@compilade.net>
2024-06-07 17:10:51 -04:00
6d3a256d1d
rename GGUFManager to GGUFWriterSplit
2024-06-07 09:12:44 -04:00
13ffe22ca7
base-1024 bytes to base-1000
2024-06-06 10:24:11 -04:00
83e4a3f5cc
make pathlib explicit
2024-06-06 09:00:59 -04:00
2037eabb64
move kv keys to constants.py
2024-06-06 08:49:46 -04:00
1cbab22225
type consistency in format_n_bytes_to_str
2024-06-06 08:43:26 -04:00
3328b0a991
Shard dataclass and un-negative dont_add_architecture
2024-06-06 08:37:35 -04:00
6a05183b97
GGUFWriter compatibility fix
...
Co-authored-by: compilade <git@compilade.net>
2024-06-06 08:28:10 -04:00
f5d7b268ec
llama : add jina v2 base code ( #7596 )
...
* feat: add changes to handle jina v2 base code
* fix: do not complicate things
* fix: fix the usage of the code model
* fix: fix comments
* fix: fix linting issues
* fix: remove ollama patches
* style : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-06-06 10:22:41 +03:00
ce7e6985d2
form shards while adding tensors, SHA256 sums agree with master
2024-06-05 18:29:39 -04:00
5ad397d610
reduce diffs with master
2024-06-05 13:49:20 -04:00
bb5ee02096
simplify even further and standardize with GGUFWriter
2024-06-05 12:49:08 -04:00
f6fd3ea4e9
further simplify GGUFManager
2024-06-05 12:28:40 -04:00
3e9430df33
reduce duplicated code from gguf_writer
2024-06-05 09:29:33 -04:00
efead0408c
fix gguf_writer placement and remove comments
2024-06-03 19:34:01 -04:00
140eb52f3f
Merge branch 'master' into convert-split
2024-06-03 09:07:23 -04:00
240243e63f
remove unnecessary imports in gguf_manager
2024-06-03 09:01:42 -04:00
09baf2f3b5
fix Q8 quantization
2024-06-03 08:58:29 -04:00
6f28a333c1
llama : MiniCPM support tied embeddings ( #7664 )
...
* support lm_head
* remove the code block
---------
Co-authored-by: zhangkaihuo <zhangkaihuo@modelbest.cn>
2024-06-03 10:49:30 +03:00
Christian Zhou-Zheng
Christian Zhou-Zheng
compilade
Joan Fontanals
zhangkaihuo