 sgsdxzy
|
589fe0c73e
fix: split the exl2 weight loading and SQ+ init (#423)
|
hai 8 meses |
 AlpinDale
|
50c2434267
move megatron to a top-level directory
|
hai 9 meses |
|
AlpinDale
|
41beab5dc1
add exllamav2 tensor paralell, fused MoE for GPTQ/AWQ
|
hai 9 meses |
|
AlpinDale
|
7b9c08afae
vision model support
|
hai 9 meses |
 AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
hai 9 meses |
|
AlpinDale
|
c2d77b1822
chore: logging refactor (#302)
|
hai 10 meses |
|
AlpinDale
|
e0c35bb353
feat: bitsandbytes and `--load-in{4,8}bit` support (#294)
|
hai 10 meses |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
hai 10 meses |
|
AlpinDale
|
697c06c4f5
fix: LoRA support for mixtral (#276)
|
hai 10 meses |
|
AlpinDale
|
224b87b484
feat: add fused mixtral moe support (#238)
|
hai 10 meses |
|
AlpinDale
|
ea0f57b233
feat: allow further support for non-cuda devices (#247)
|
hai 11 meses |
|
AlpinDale
|
4faf78ba29
fix: grab correct quant config from revisions (#246)
|
hai 11 meses |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
hai 11 meses |
|
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
hai 1 ano |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
hai 1 ano |
|
AlpinDale
|
989df2d84b
add Yi to quantized models
|
hai 1 ano |
|
AlpinDale
|
e59e7f0a99
feat: yi support (#104)
|
hai 1 ano |
|
AlpinDale
|
74604eb252
fix: pylint complaints (#91)
|
hai 1 ano |
|
AlpinDale
|
efc6f7fbec
chore: reformats (#90)
|
hai 1 ano |
|
AlpinDale
|
f73f2dd3c2
feat: add mistral support for GPTQ (#86)
|
hai 1 ano |
|
AlpinDale
|
f04588203e
feat: mistral AWQ support and file blacklisting
|
hai 1 ano |
|
AlpinDale
|
0495c50a3e
GPTQ+exllama support (#21)
|
hai 1 ano |
|
AlpinDale
|
cbeeabeb9a
feat: mistral support (#20)
|
hai 1 ano |
|
AlpinDale
|
1ab15649ae
fix column parallelism in quantized layers
|
hai 1 ano |
|
AlpinDale
|
75c27d3e65
massive overhaul
|
hai 1 ano |
|
AlpinDale
|
c95d80da39
fix revision issues
|
hai 1 ano |
|
AlpinDale
|
0a54cd7e26
dict to list
|
hai 1 ano |
|
AlpinDale
|
d9c1d4f6e5
add awq support
|
hai 1 ano |
|
AlpinDale
|
58c11e2178
remove revision from the loader
|
hai 1 ano |
|
AlpinDale
|
39beed0b87
Revert "Refactor AWQ support."
|
hai 1 ano |
