 Gabe Goodhart
|
3d6bf6919f
llama : add IBM Granite MoE architecture (#9438)
|
1 жил өмнө |
|
Gabe Goodhart
|
0d2ec43833
llama : support IBM Granite architecture (#9412)
|
1 жил өмнө |
 compilade
|
d54c21df7e
convert : identify missing model files (#9397)
|
1 жил өмнө |
 Shane A
|
0aadac10c7
llama : support OLMoE (#9462)
|
1 жил өмнө |
 CarryFun
|
95ca85168b
llama : support MiniCPM3 (#9322)
|
1 жил өмнө |
 Csaba Kecskemeti
|
3c7989fd29
py : add "LLaMAForCausalLM" conversion support (#9485)
|
1 жил өмнө |
 daminho
|
c837981bba
py : add Phi-1.5/Phi-2 tokenizer (#9361)
|
1 жил өмнө |
 Molly Sophia
|
39f852f440
py : add special tokens in hf_converter for RWKV v6 (#9428)
|
1 жил өмнө |
|
Molly Sophia
|
0b4ac75772
RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list (#9387)
|
1 жил өмнө |
|
compilade
|
9bc6db28d0
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
|
1 жил өмнө |
|
Molly Sophia
|
8f1d81a0b6
llama : support RWKV v6 models (#8980)
|
1 жил өмнө |
 Carsten Kragelund Jørgensen
|
75e1dbbaab
llama : fix llama3.1 rope_freqs not respecting custom head_dim (#9141)
|
1 жил өмнө |
 Xuan Son Nguyen
|
3ba780e2a8
lora : fix llama conversion script with ROPE_FREQS (#9117)
|
1 жил өмнө |
 Younes Belkada
|
b40eb84895
llama : support for `falcon-mamba` architecture (#9074)
|
1 жил өмнө |
 Minsoo Cheong
|
c679e0cb5c
llama : add EXAONE model support (#9025)
|
1 жил өмнө |
 Yoshi Suhara
|
2a24c8caa6
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
|
1 жил өмнө |
 Esko Toivonen
|
6bda7ce6c3
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)
|
1 жил өмнө |
 fairydreaming
|
7c3f55c100
Add support for encoder-only T5 models (#8900)
|
1 жил өмнө |
|
compilade
|
3a14e00366
gguf-py : simplify support for quant types (#8838)
|
1 жил өмнө |
 Douglas Hanley
|
cdd1889de6
convert : add support for XLMRoberta embedding models (#8658)
|
1 жил өмнө |
 Sigbjørn Skjæret
|
b72c20b85c
Fix conversion of unnormalized BF16->BF16 weights (#7843)
|
1 жил өмнө |
 Jeffrey Morgan
|
b5e95468b1
llama : add support for llama 3.1 rope scaling factors (#8676)
|
1 жил өмнө |
 Fan Shupei
|
8a4bad50a8
llama: use sliding window for phi3 (#8627)
|
1 жил өмнө |
 Keke Han
|
081fe431aa
llama : fix codeshell support (#8599)
|
1 жил өмнө |
 Jason Stillerman
|
d94c6e0ccb
llama : add support for SmolLm pre-tokenizer (#8609)
|
1 жил өмнө |
 Jiří Podivín
|
566daa5a5b
*.py: Stylistic adjustments for python (#8233)
|
1 жил өмнө |
|
Douglas Hanley
|
50e05353e8
llama : add Mistral Nemo inference support (#8604)
|
1 жил өмнө |
|
compilade
|
328884f421
gguf-py : fix some metadata name extraction edge cases (#8591)
|
1 жил өмнө |
|
compilade
|
c69c63039c
convert_hf : fix Gemma v1 conversion (#8597)
|
1 жил өмнө |
 Michael Coppola
|
940362224d
llama : add support for Tekken pre-tokenizer (#8579)
|
1 жил өмнө |
