 Shane A
|
80acb7b430
Rename Olmo1124 to Olmo2 (#10500)
|
1 anno fa |
 Gabe Goodhart
|
9336db462c
convert : XLMRoberta Type Vocab Size (#10458)
|
1 anno fa |
|
Shane A
|
a88ad007de
llama : add OLMo November 2024 support (#10394)
|
1 anno fa |
 Faisal Zaghloul
|
60e17ce23c
Remove identical wte/etw logic for jais (#10203)
|
1 anno fa |
 Xuan Son Nguyen
|
7554aa4655
convert-lora : make `--base` optional (#10110)
|
1 anno fa |
 Georgi Gerganov
|
bc5ba007b2
server : check that the prompt fits in the slot's context (#10030)
|
1 anno fa |
 Molly Sophia
|
11d47057a5
Rwkv chat template fix (#10001)
|
1 anno fa |
|
Molly Sophia
|
4ff7fe1fb3
llama : add chat template for RWKV-World + fix EOT (#9968)
|
1 anno fa |
 compilade
|
1927378bcc
convert : refactor rope_freqs generation (#9396)
|
1 anno fa |
 nopperl
|
f99d3f8367
py : add model class for Chameleon conversion (#9683)
|
1 anno fa |
|
Georgi Gerganov
|
f4d2b8846a
llama : add reranking support (#9510)
|
1 anno fa |
|
nopperl
|
9a913110cf
llama : add support for Chameleon (#8543)
|
1 anno fa |
|
Gabe Goodhart
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
1 anno fa |
|
Gabe Goodhart
|
0d2ec43833
llama : support IBM Granite architecture (#9412)
|
1 anno fa |
|
compilade
|
d54c21df7e
convert : identify missing model files (#9397)
|
1 anno fa |
|
Shane A
|
0aadac10c7
llama : support OLMoE (#9462)
|
1 anno fa |
 CarryFun
|
95ca85168b
llama : support MiniCPM3 (#9322)
|
1 anno fa |
 Csaba Kecskemeti
|
3c7989fd29
py : add "LLaMAForCausalLM" conversion support (#9485)
|
1 anno fa |
 daminho
|
c837981bba
py : add Phi-1.5/Phi-2 tokenizer (#9361)
|
1 anno fa |
|
Molly Sophia
|
39f852f440
py : add special tokens in hf_converter for RWKV v6 (#9428)
|
1 anno fa |
|
Molly Sophia
|
0b4ac75772
RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list (#9387)
|
1 anno fa |
|
compilade
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 anno fa |
|
Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 anno fa |
 Carsten Kragelund Jørgensen
|
75e1dbbaab
llama : fix llama3.1 rope_freqs not respecting custom head_dim (#9141)
|
1 anno fa |
|
Xuan Son Nguyen
|
3ba780e2a8
lora : fix llama conversion script with ROPE_FREQS (#9117)
|
1 anno fa |
 Younes Belkada
|
b40eb84895
llama : support for `falcon-mamba` architecture (#9074)
|
1 anno fa |
 Minsoo Cheong
|
c679e0cb5c
llama : add EXAONE model support (#9025)
|
1 anno fa |
 Yoshi Suhara
|
2a24c8caa6
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
|
1 anno fa |
 Esko Toivonen
|
6bda7ce6c3
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)
|
1 anno fa |
 fairydreaming
|
7c3f55c100
Add support for encoder-only T5 models (#8900)
|
1 anno fa |
