StyMaar
978f6e1993
Update gguf specification to synchronize the ggml_types declaration shown in the doc with the actual one. ( #1342 )
...
BF16, TQ1_0,TQ2_0 and MXFP4 were missing in the enum declaration in the spec.
2025-09-16 13:42:24 +02:00
Georgi Gerganov
d50c1fff85
media : rm logos ( #1203 )
...
* media : add
* media : experiment with cards
* media : add common.sh
* cards : fix frame and shadow
* cards : adjustments
* cards : add qwen3
* media : rm
2025-04-30 08:05:22 +03:00
Brian
f18a111977
gguf.md: naming convention synced to llama.cpp ( #896 )
...
It is now updated to this form
`<BaseName><SizeLabel><FineTune><Version><Encoding><Type><Shard>.gguf`
2024-07-22 13:25:01 +03:00
Brian
a44ac4e48e
gguf.md: kv store has new authorship metadata keys ( #897 )
2024-07-21 11:20:30 +03:00
compilade
8d6b703887
gguf : use Qn_K for k-quants instead of KQn ( #837 )
2024-05-24 23:58:29 +03:00
Brian
0cbb7c0e05
gguf.md: add sharding to naming convention ( #826 )
...
* gguf.md: add sharding to naming convention [no ci]
* gguf.md: Add note on using gguf metadata for model name, version and expert count [no ci]
* gguf.md: Tighten up wording and add regex example [no ci]
* gguf.md: json output for expertcount and shard is numerical [no ci]
2024-05-19 11:05:26 +03:00
Brian
9988298d9a
gguf.md: Add GGUF Naming Convention Section ( #822 )
...
* gguf.md: Add GGUF Naming Convention Section
* gguf.md: add BF16
* gguf.md: GGUF Filename Parsing Strategy
* gguf.md: include tensor type table and historical context
* gguf.md: minor corrections
* gguf.md: more detailed breakdown of tensor type mapping
* gguf.md: use Encoding Scheme name instead
* gguf.md: minor correction to overall naming convention
* gguf.md: simplify GGUF Naming Convention
2024-05-17 09:09:01 +03:00
Daniel Bevenius
e1daebbf9d
spec : fix typo in gguf.md ( #798 )
...
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-04-18 19:47:17 +03:00
Georgi Gerganov
48d64d932c
logo : add files ( #782 )
2024-04-03 22:59:55 +03:00
JacobLinCool
795de7bc58
gguf : update type enum ( #775 )
...
* spec: add missing semicolons in GGUF structs
Co-Authored-By: 郝東彥 Arthur Hao <41247050s@gapps.ntnu.edu.tw>
* spec: update GGUF tensor types
---------
Co-authored-by: 郝東彥 Arthur Hao <41247050s@gapps.ntnu.edu.tw>
2024-03-27 19:48:56 +02:00
Georgi Gerganov
ef085b5a8c
spec : add GGUF diagram ( #765 )
2024-03-15 14:10:35 +02:00
compilade
9c2adc4962
gguf : add Mamba keys and tensors ( #763 )
2024-03-13 16:33:19 +02:00
postmasters
9e221033f3
gguf : add keys for kv sizes to spec ( #676 )
...
* Add keys for kv sizes to GGUF spec
* Fix types of key_length and value_length
2024-01-05 17:25:38 +02:00
ariez-xyz
a027a92c1d
gguf : document Mixtral changes in spec ( #646 )
...
* add new tensor names
* add new keys
* fix tensor names
* gguf : change wording a bit
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-12-13 14:01:31 +02:00
slaren
57c468b865
gguf : add tokenizer.chat_template documentation ( #616 )
2023-11-19 10:37:08 +02:00
Philpax
54cec9f619
gguf : add file format specification ( #302 )
...
* docs: gguf spec first pass
* docs(gguf): update with review comments
* docs(gguf): update with review comments
* docs(gguf): quant version optional for unquant
* docs(gguf): normalize naming, add whisper
* docs(gguf): more review updates
* docs(gguf): add norm eps and added_tokens
* docs(gguf): move padding
* docs(gguf): remove migration tool
* docs(gguf): make offset base explicit
* docs(gguf): fix replace oops
* docs(gguf): alignment metadata+tensor name len max
* docs(gguf): clarification, fixes, tensor names
* docs(gguf): clarify license
* docs(gguf): minor tweaks
* docs(gguf): data layout, GQA eq, no ft, LE GGUF
* docs(gguf): fix magic order
* docs(gguf): match impl
* docs(gguf): specify fallback alignment
* docs(gguf): remove TensorInfo::n_elements
* docs(gguf): filetype, rope base/linear scale
* docs(gguf): v2 - uint64 all the things
* docs(gguf): tweak extensibility wording
* docs(gguf): fix spec discrepancies
* docs(gguf): v3 + other fixes
* fix(editorconfig): use 2-space tabs for markdown
* docs(gguf): clarify big-endian
2023-11-01 19:01:49 +02:00
