Pierrick HYMBERT
50b4373673
model: dbrx: weird fix expert reshape
2024-04-07 20:14:43 +02:00
Pierrick HYMBERT
e2c919962b
model: dbrx: fix again sic expert reshape
2024-04-07 20:10:16 +02:00
Pierrick HYMBERT
c9bddbf253
model: dbrx: fix expert reshape
2024-04-07 19:38:35 +02:00
DAN™
e0717e751e
Add GritLM as supported models. ( #6513 )
2024-04-07 19:33:59 +02:00
Pierrick HYMBERT
7dd84b0924
model: dbrx: fix expert reshape
2024-04-07 19:12:24 +02:00
Pierrick HYMBERT
dbfd59114f
model: dbrx: fix tensor names mapping broken
2024-04-07 18:52:28 +02:00
Pierrick HYMBERT
f062b834ed
model: dbrx: convert experts to f16
2024-04-07 18:47:37 +02:00
Pierrick HYMBERT
d151d8fad9
model: dbrx: convert reshape expert tensors to 3D
2024-04-07 18:41:33 +02:00
Pierrick HYMBERT
e9987c66d0
llama: dbrx: fix tensor qkv number of elements
2024-04-07 18:21:57 +02:00
Pierrick HYMBERT
1bd94270e5
llama: quantize: remove wrong look for tensor qkv name as it was badly missing the .weight suffix
...
model: dbrx: convert to gguf force experts tensors to have .weight suffix
2024-04-07 17:55:33 +02:00
Pierrick HYMBERT
2449ef48a9
llama: dbrx: no weight suffix in ffn_gate_exps, ffn_up_exps and ffn_down_exps. Output tensor not optional.
2024-04-07 17:55:33 +02:00
Pierrick HYMBERT
8154617ff2
model: dbrx: convert-hf-to-gguf.py support python 3.8
2024-04-07 17:25:39 +02:00
Pierrick HYMBERT
3a9dc2eee2
model: dbrx: convert-hf-to-gguf.py fix 'token_embd.weight' has wrong shape, fix special tokens
2024-04-07 17:21:35 +02:00
Georgi Gerganov
c37247796b
sync : ggml
2024-04-07 17:05:51 +03:00
Slava Primenko
f77261a7c5
ggml: bypass code incompatible with CUDA < 11.1 (whisper/2020)
...
`cudaHostRegisterReadOnly` parameter was only introduced in CUDA 11.1
See this issue for more details:
https://github.com/ggerganov/examples/whisper/whisper.cpp/issues/2007
2024-04-07 17:05:40 +03:00
Pierrick HYMBERT
d7546fda64
llama: quantize: remove wrong look for tensor qkv name as it was badly missing the .weight suffix
2024-04-07 15:59:07 +02:00
Pierrick HYMBERT
9e17dad087
model: dbrx: convert-hf-to-gguf.py add chat template
2024-04-07 15:57:36 +02:00
Pierrick HYMBERT
200ce21436
model: dbrx: convert-hf-to-gguf.py fix fix ftype missing, fix tensor names does not suffix with .weight
2024-04-07 15:54:19 +02:00
Pierrick HYMBERT
1fb6d95c1d
model: convert-hf-to-gguf.py fix classname conflict with qwen2
2024-04-07 15:40:21 +02:00
Georgi Gerganov
43e8995e75
scripts : sync ggml-cuda folder
2024-04-07 16:08:12 +03:00
limitedAtonement
9472bce308
Run make to build the project ( #6457 )
2024-04-07 13:05:40 +02:00
Pierrick HYMBERT
61be4b91a6
model: convert-hf-to-gguf.py add _set_vocab_tiktoken gpt2 backed on llama.cpp
2024-04-07 12:15:16 +02:00
Pierrick HYMBERT
dccb012637
llama: dbrx: quantize fix n_attention_wv tensor name
2024-04-07 05:09:17 +02:00
Pierrick HYMBERT
b6522a9f5b
model: dbrx: convert fix tokenizer
2024-04-07 05:02:14 +02:00
Pierrick HYMBERT
305ac3b61b
llama: dbrx: quantize fix n_attention_wv tensor name
2024-04-07 05:01:33 +02:00
Neo Zhang Jianyu
d4f220a5cc
support/fix OPs GGML_TYPE_IQ4_NL, GGML_TYPE_IQ4_XS, GGML_TYPE_IQ3_XXS, GGML_TYPE_IQ3_S, GGML_TYPE_IQ2_XXS, GGML_TYPE_IQ2_XS, GGML_TYPE_IQ2_S, GGML_TYPE_IQ1_S, GGML_TYPE_IQ1_M ( #6521 )
2024-04-07 10:55:59 +08:00
Pierrick HYMBERT
06a59abf0a
model: dbrx: convert add n_ff
2024-04-07 03:17:24 +02:00
Pierrick HYMBERT
52c403355f
llama: increase maximum experts allowed
2024-04-07 03:16:33 +02:00
Pierrick HYMBERT
7e7cd53ca6
llama: dbrx: remove unnecessary optional tensor on FFN_GATE_EXPS
2024-04-06 23:55:37 +02:00
Pierrick HYMBERT
69856297b9
Merge remote-tracking branch 'origin/master' into hp/model/support-dbrx
2024-04-06 23:53:11 +02:00
Pierrick HYMBERT
4f12a580d9
llama: dbrx: remove not existing condition on empty output layer
2024-04-06 23:35:23 +02:00
Pierrick HYMBERT
fe8089871e
model: dbrx: fix missing embedding tensor, mix with output layer
2024-04-06 23:27:29 +02:00
Pierrick HYMBERT
9c7dedb0f3
llama: dbrx: no attention output layer
2024-04-06 22:25:37 +02:00
Pierrick HYMBERT
76f266beef
scripts: get-wikitext-2 add unzip
2024-04-06 21:10:19 +02:00
Pierrick HYMBERT
03da419fc0
llama: dbrx: remove wrong attn output layer in model arch
2024-04-06 20:43:46 +02:00
Pierrick HYMBERT
916b91852b
convert: dbrx: fix remove wrong ATTN_OUT_NORM tensor, add output layer mapping
2024-04-06 20:30:30 +02:00
Pierrick HYMBERT
c8e6f903e0
doc: dbrx: add the model as supported
2024-04-06 20:09:01 +02:00
Pierrick HYMBERT
0a35f5881b
convert: dbrx: fix mixed up and down expert tensors
...
llama: dbrx: review graph
2024-04-06 19:56:37 +02:00
Pierrick HYMBERT
e3c1e8127c
convert: dbrx: fix mixed up and down expert tensors
2024-04-06 19:21:43 +02:00
Pierrick HYMBERT
a7f9a3eafc
dbrx: minor
2024-04-06 19:09:04 +02:00
Georgi Gerganov
54ea0698fb
sync : ggml
2024-04-06 18:27:46 +03:00
Daniel Bevenius
b66aec675c
backend : fix typo in scheduler documentation (ggml/781)
...
Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
2024-04-06 17:42:26 +03:00
Clint Herron
57dd02c44b
Tests: Added integration tests for GBNF parser ( #6472 )
...
* Added integration tests for GBNF parser to validate correctness of parsing, as well as correctness of string matching. Intended for use to pin behavior while working on performance improvements.
* Fixing whitespace errors and cleaning error message alert to be clearer.
* Removing hacky include to llama.cpp from grammar integration test now that needed functions are available via internal API.
* Comment cleanup.
* Reorganizing tests for readability.
* Cleaning up debug message to make a bit more sense.
2024-04-06 10:31:33 -04:00
Pierrick HYMBERT
e4f8ee4f48
llama: support dbrx fix norm type
2024-04-06 16:14:58 +02:00
Pierrick HYMBERT
09210334bf
model: dbrx fix python linter in convert-hf-to-gguf.py
2024-04-06 16:00:32 +02:00
Pierrick HYMBERT
c0beb3cf7e
llama: add label for model 132B
2024-04-06 15:58:17 +02:00
Pierrick HYMBERT
3937100adb
model: dbrx, trust remote code
2024-04-06 15:57:57 +02:00
Pierrick HYMBERT
3e3d2d127c
gguf-py: remove wrong clip -> clamp
2024-04-06 15:46:47 +02:00
Pierrick HYMBERT
ed582c1dde
llama: support dbrx
...
#6344
2024-04-06 15:22:55 +02:00
Pierrick HYMBERT
1d8de31565
model: dbrx convert to gguf
...
#6344
2024-04-06 14:17:24 +02:00
