 isHuangXin
|
69bf64d373
|
Add bitnet-embeddings-0.6b model adaptation with F16 and I2_S GGUF conversion
- Add GGUF conversion tool for bitnet-embeddings-0.6b (safetensors -> F16/I2_S GGUF)
- Add Qwen3 architecture support in llama.cpp submodule with per-projection RMSNorm
- Add I2_S ternary quantization (2-bit packed -1/0/+1) for lossless precision
- Add f16 norm weight support for correct embedding inference
- Guard bitnet-lut-kernels.h include with TL1/TL2 preprocessor checks
- Update llama.cpp submodule to dev-bitnet-embedding-0.6b branch
- Document F16 (from multilingual-e5-0.6b) and I2_S (from bitnet-embeddings-0.6b) conversion process
|
2026-07-12 04:10:30 +02:00 |
|
|
XSquirrelC
|
1876a3e889
|
[merge] submodule llama.cpp
|
2026-01-27 03:09:32 +00:00 |
|
|
deva100
|
112f853414
|
[feat] I2S kernels for weight & activation parallel on Intel & ARM machine; [feat] I2S GEMV & GEMM(llama.cpp); [feat] quantize activation & dequantize embedding(llama.cpp); [fix] compile bug: cannot define __ARM_FEATURE_DOTPROD(llama.cpp)
|
2025-11-19 07:35:05 +00:00 |
|
|
younesbelkada
|
765741d80b
|
update submodule
|
2025-05-21 11:52:30 +04:00 |
|
|
junhuihe
|
488dc1e876
|
Fix model architecture name
|
2025-04-22 17:28:59 +08:00 |
|
|
potassiummmm
|
4f2e41a514
|
add support for bitnet2b_2501 model
|
2025-03-12 18:16:45 +08:00 |
|
|
potassiummmm
|
aa39c0cdcc
|
fix version requirement of transformers pypi package and model list for codegen
|
2024-12-18 17:54:23 +08:00 |
|
|
younesbelkada
|
c1892d6818
|
updated submodule
|
2024-11-14 14:53:43 +00:00 |
|
|
potassiummmm
|
bf11a49f11
|
Add support for ios platform
|
2024-11-11 15:13:55 +08:00 |
|
|
Eddie-Wang1120
|
c82b5e6674
|
update 3rdparty/llama.cpp
|
2024-10-18 10:08:22 +08:00 |
|
|
potassiummmm
|
6cfd8831fd
|
initial commit
|
2024-10-17 21:21:10 +08:00 |
|