 Gabe Goodhart
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
1 jaar geleden |
|
Gabe Goodhart
|
0d2ec43833
llama : support IBM Granite architecture (#9412)
|
1 jaar geleden |
 Shane A
|
0aadac10c7
llama : support OLMoE (#9462)
|
1 jaar geleden |
 CarryFun
|
95ca85168b
llama : support MiniCPM3 (#9322)
|
1 jaar geleden |
 compilade
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 jaar geleden |
 Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 jaar geleden |
 Younes Belkada
|
b40eb84895
llama : support for `falcon-mamba` architecture (#9074)
|
1 jaar geleden |
 Minsoo Cheong
|
c679e0cb5c
llama : add EXAONE model support (#9025)
|
1 jaar geleden |
 Yoshi Suhara
|
2a24c8caa6
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
|
1 jaar geleden |
 fairydreaming
|
7c3f55c100
Add support for encoder-only T5 models (#8900)
|
1 jaar geleden |
|
compilade
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
1 jaar geleden |
|
fairydreaming
|
d3f0c7166a
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)
|
1 jaar geleden |
 Brian
|
672a6f1018
convert-*.py: GGUF Naming Convention Refactor and Metadata Override Refactor (#7499)
|
1 jaar geleden |
 Xuan Son Nguyen
|
97bdd26eee
Refactor lora adapter support (#8332)
|
1 jaar geleden |
 toyer
|
905942abdb
llama : support glm3 and glm4 (#8031)
|
1 jaar geleden |
 Icecream95
|
d7fd29fff1
llama : add OpenELM support (#7359)
|
1 jaar geleden |
 Faisal Zaghloul
|
968967376d
Add `JAIS` model(s) (#8118)
|
1 jaar geleden |
|
Xuan Son Nguyen
|
49122a873f
gemma2: add sliding window mask (#8227)
|
1 jaar geleden |
 Andrei
|
1c5eba6f8e
llama: Add attention and final logit soft-capping, update scaling factor to Gemma2 (#8197)
|
1 jaar geleden |
 pculliton
|
e57dc62057
llama: Add support for Gemma2ForCausalLM (#8156)
|
1 jaar geleden |
 Christian Zhou-Zheng
|
52fc8705a0
Option to split during conversion (#6942)
|
1 jaar geleden |
|
fairydreaming
|
de0d6a68ac
gguf-py, convert-hf : model conversion support for T5 and FLAN-T5 model variants (#5763)
|
1 jaar geleden |
 Eddie-Wang
|
e112b610a1
llama : add support for BitnetForCausalLM (#7931)
|
1 jaar geleden |
 Ștefan-Gabriel Muscalu
|
a94e6ff877
update: support Qwen2-57B-A14B (#7835)
|
1 jaar geleden |
 Joan Fontanals
|
f5d7b268ec
llama : add jina v2 base code (#7596)
|
1 jaar geleden |
 zhangkaihuo
|
6f28a333c1
llama : MiniCPM support tied embeddings (#7664)
|
1 jaar geleden |
|
fairydreaming
|
ee3dff6b8e
Add support for DeepseekV2ForCausalLM (#7519)
|
1 jaar geleden |
|
fairydreaming
|
fbca2f27fc
Add support for ArcticForCausalLM (#7020)
|
1 jaar geleden |
 Georgi Gerganov
|
e84b71c2c6
ggml : drop support for QK_K=64 (#7473)
|
1 jaar geleden |
 liuwei-git
|
201cc11afa
llama : add phi3 128K model support (#7225)
|
1 jaar geleden |
