Update README.md
#24 opened about 1 year ago
by
VGS52
newest llama.cpp seems to crash now
7
#21 opened over 1 year ago
by
WizardDave
lora
#20 opened over 1 year ago
by
wanghao-007
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Nr7UaTDsEd2IqdNsyojTQ.jpeg)
Commercial use
3
#18 opened over 1 year ago
by
Codgas
How to run these quantised model.
4
#17 opened over 1 year ago
by
Tarun1986
uncensored version
8
#16 opened over 1 year ago
by
Feng7815
Request for Code to Fine-Tune the Vicuna Model
#15 opened over 1 year ago
by
bouam511
ggml-vic13b-uncensored-q5_1.bin and ggml-vic13b-uncensored-q8_0.bin throw errors in newest oobabooga-webui
2
#14 opened over 1 year ago
by
RandomLegend
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1663749541206-63184e6f1db54eb64dc6f4ff.png)
AMD GPU Support?
1
#12 opened over 1 year ago
by
Wats0n
Will a 1.1-uncensored follow?
3
#11 opened over 1 year ago
by
Wubbbi
ggml-vicuna-13b-1.1-q4_3 unrecognized tensor type 5
6
#10 opened over 1 year ago
by
NicRaf
vicuna 1.1 13b q4_1 failed to load (bad float16)
2
#9 opened over 1 year ago
by
couchpotato888
Can the quantized model support Chinese?
1
#8 opened over 1 year ago
by
FancyPig
How to get running using fastchat on a m1 mac?
3
#7 opened over 1 year ago
by
kkostecky
is there a compiled list of token speed optimization methods yet?
#6 opened over 1 year ago
by
Alignment-Lab-AI
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6436279eaaef013d1af225c9/31yjIFpqfdvn_n9igumIU.png)
4bit-32g vs 4-bit 128g ?
2
#5 opened over 1 year ago
by
nucleardiffusion
Memory requirement for 13B 4Bit
1
#4 opened over 1 year ago
by
afoam
SOLVED Running this v1.1 on llama.cpp
2
#3 opened over 1 year ago
by
JeroenAdam
Optimal context to provide after tokenization change
1
#2 opened over 1 year ago
by
IonizedLeaf
where could get 30B
1
#1 opened over 1 year ago
by
baby1