 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
|
3987a503fd
|
[fix] convert pt to gguf
|
2026-02-03 05:24:24 +00:00 |
|
|
XSquirrelC
|
e8c8107dcf
|
[modify] some test picture and add power test script
|
2026-01-25 06:51:33 +00:00 |
|
|
XSquirrelC
|
7b2c52b9d5
|
[modify] some utils test script
|
2026-01-24 08:40:36 +00:00 |
|
|
deva100
|
7e6f0e14f1
|
[modify] update README; [feat] some test script in utils
|
2026-01-22 06:33:03 +00:00 |
|
|
junhuihe
|
43e9b2d4a0
|
Enable conversion from .safetensors checkpoints to gguf files
|
2025-05-23 16:19:29 +08:00 |
|
|
younesbelkada
|
de371b708d
|
add falcon-e support
|
2025-05-14 17:07:05 +04:00 |
|
|
potassiummmm
|
09f91066d6
|
add conversion logic for new model
|
2025-03-12 18:34:05 +08:00 |
|
|
younesbelkada
|
a838911a55
|
more changes to support chat models
|
2024-12-09 16:45:31 +00:00 |
|
|
younesbelkada
|
7c57a5ae20
|
fix weird character issue
|
2024-11-23 14:49:44 +00:00 |
|
|
younesbelkada
|
18cfa8af89
|
add fc3 support
|
2024-11-14 14:51:09 +00:00 |
|
|
potassiummmm
|
338973feb8
|
Merge pull request #83 from JCGoran/jelic/gcc_fixes
Fix building on GCC toolchain
|
2024-11-07 00:29:17 +08:00 |
|
|
potassiummmm
|
80b94aecb2
|
Fix llama-bench path error on Windows
|
2024-10-31 16:50:47 +08:00 |
|
|
Goran Jelic-Cizmek
|
141ddfd4fe
|
Fix compiler errors on GCC
|
2024-10-25 16:23:01 +02:00 |
|
|
potassiummmm
|
6cfd8831fd
|
initial commit
|
2024-10-17 21:21:10 +08:00 |
|