COMMITS
/ convert_hf_to_gguf.py December 7, 2024
R
llama : add 128k yarn context for Qwen (#10698)
Robert Collins committed
S
convert : add support for Roberta embeddings (#10695)
Sukriti Sharma committed
December 5, 2024
R
llama : add Minerva 7B model support (#10673)
Riccardo Orlando committed
December 4, 2024
J
llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
JFLFY2255 committed
November 25, 2024
S
Rename Olmo1124 to Olmo2 (#10500)
Shane A committed
November 24, 2024
G
convert : XLMRoberta Type Vocab Size (#10458)
Gabe Goodhart committed
November 19, 2024
S
llama : add OLMo November 2024 support (#10394)
Shane A committed
November 7, 2024
F
Remove identical wte/etw logic for jais (#10203)
Faisal Zaghloul committed
November 2, 2024
X
convert-lora : make `--base` optional (#10110)
Xuan Son Nguyen committed
October 25, 2024
G
server : check that the prompt fits in the slot's context (#10030)
Georgi Gerganov committed
October 22, 2024
M
Rwkv chat template fix (#10001)
Molly Sophia committed
M
llama : add chat template for RWKV-World + fix EOT (#9968)
Molly Sophia committed
October 1, 2024
C
convert : refactor rope_freqs generation (#9396)
compilade committed
September 29, 2024
N
py : add model class for Chameleon conversion (#9683)
nopperl committed
September 28, 2024
G
llama : add reranking support (#9510)
Georgi Gerganov committed
N
llama : add support for Chameleon (#8543)
nopperl committed
September 25, 2024
G
llama : add IBM Granite MoE architecture (#9438)
Gabe Goodhart committed
September 17, 2024
G
llama : support IBM Granite architecture (#9412)
Gabe Goodhart committed
September 16, 2024
C
convert : identify missing model files (#9397)
compilade committed
S
llama : support OLMoE (#9462)
Shane A committed
C
llama : support MiniCPM3 (#9322)
CarryFun committed
September 15, 2024
C
py : add "LLaMAForCausalLM" conversion support (#9485)
Csaba Kecskemeti committed
September 12, 2024
D
py : add Phi-1.5/Phi-2 tokenizer (#9361)
daminho committed
M
py : add special tokens in hf_converter for RWKV v6 (#9428)
Molly Sophia committed
September 10, 2024
M
RWKV v6: Add time_mix_decay_w1/w2 in quant exclusion list (#9387)
Molly Sophia committed
September 6, 2024
C
ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
compilade committed
September 1, 2024
M
llama : support RWKV v6 models (#8980)
Molly Sophia committed
August 27, 2024
C
llama : fix llama3.1 rope_freqs not respecting custom head_dim (#9141)
Carsten Kragelund Jørgensen committed
August 23, 2024
X
lora : fix llama conversion script with ROPE_FREQS (#9117)
Xuan Son Nguyen committed
August 21, 2024
Y
llama : support for `falcon-mamba` architecture (#9074)
Younes Belkada committed
August 16, 2024
M
llama : add EXAONE model support (#9025)
Minsoo Cheong committed
Y
Add Nemotron/Minitron GGUF Conversion & Inference Support (#8922)
Yoshi Suhara committed
August 15, 2024
E
llama : add pre-tokenizer regexes for BLOOM and gpt3-finnish (#8850)
Esko Toivonen committed
August 10, 2024
F
Add support for encoder-only T5 models (#8900)
fairydreaming committed
August 8, 2024
C
gguf-py : simplify support for quant types (#8838)
compilade committed
August 6, 2024
D
convert : add support for XLMRoberta embedding models (#8658)
Douglas Hanley committed
August 2, 2024
S
Fix conversion of unnormalized BF16->BF16 weights (#7843)
Sigbjørn Skjæret committed
July 27, 2024
J
llama : add support for llama 3.1 rope scaling factors (#8676)
Jeffrey Morgan committed
July 25, 2024
F
llama: use sliding window for phi3 (#8627)
Fan Shupei committed
July 22, 2024
K
llama : fix codeshell support (#8599)
Keke Han committed
J
llama : add support for SmolLm pre-tokenizer (#8609)
Jason Stillerman committed
J
*.py: Stylistic adjustments for python (#8233)
Jiří Podivín committed
D
llama : add Mistral Nemo inference support (#8604)
Douglas Hanley committed
July 21, 2024
C
gguf-py : fix some metadata name extraction edge cases (#8591)
compilade committed
C
convert_hf : fix Gemma v1 conversion (#8597)
compilade committed
July 20, 2024
M
llama : add support for Tekken pre-tokenizer (#8579)
Michael Coppola committed
July 19, 2024
B
convert-*.py: remove add_name from ChatGLMModel class (#8590)
Brian committed
July 18, 2024
July 16, 2024
C
convert_hf : faster lazy safetensors (#8482)
compilade committed
July 15, 2024
X
Refactor lora adapter support (#8332)
Xuan Son Nguyen committed