Denied permission to DL
11
#51 opened 7 months ago
by
TimPine
request to access is still pending a review
31
#50 opened 7 months ago
by
Hoo1196
mlx_lm.server gives wonky answers
1
#49 opened 7 months ago
by
conleysa
Tokenizer mismatch all the time
2
#47 opened 7 months ago
by
tian9
Could anyone can tell me how to set the prompt template when i use the model in the pycharm by transformers?
1
#46 opened 7 months ago
by
LAKSERS
Instruct format?
3
#44 opened 7 months ago
by
m-conrad-202
MPS support quantification
5
#39 opened 7 months ago
by
tonimelisma
`meta-llama/Meta-Llama-3-8B-Instruct` model with sagemaker
1
#38 opened 7 months ago
by
aak7912
Problem with the tokenizer
2
#37 opened 7 months ago
by
Douedos
how to output an answer without side chatter
8
#36 opened 7 months ago
by
Gerald001
ValueError: You can't train a model that has been loaded in 8-bit precision on a different device than the one you're training on.
11
#35 opened 7 months ago
by
madhurjindal
Does instruct need add_generation_prompt?
1
#33 opened 7 months ago
by
bdambrosio
Error while downloading the model
3
#32 opened 7 months ago
by
amarnadh1998
Garbage responses
2
#30 opened 7 months ago
by
RainmakerP
GPU requirements
10
#29 opened 7 months ago
by
Gerald001
can I run it on CPU ?
5
#28 opened 7 months ago
by
aljbali
ChatLLM.cpp fully supports Llama-3 now
#24 opened 7 months ago
by
J22
Transformers pipeline update please
#23 opened 7 months ago
by
ip210
The best 8B in the planet right now. PERIOD!
2
#22 opened 7 months ago
by
cyberneticos
Is it really good?
5
#20 opened 7 months ago
by
urtuuuu
The result for Llama 2 13B's GSM-8K (8-shot, CoT) is 77.4, which seems incorrect.
2
#19 opened 7 months ago
by
Hi-archer
how is possible to create images with llama 3
5
#17 opened 7 months ago
by
robinaicol
OMG insomnia in the community
#16 opened 7 months ago
by
Languido
It's like Christmas without December! 🌲🎁🤖
#15 opened 7 months ago
by
Joseph717171
What is the conversation template?
8
#14 opened 7 months ago
by
aeminkocal
Update numbering format of Prohibited Uses
#13 opened 7 months ago
by
BallisticAI
Max output tokens?
3
#12 opened 7 months ago
by
stri8ted
IAM READYYYYYY
2
#3 opened 7 months ago
by
10100101j
Non-English language capabilities
6
#2 opened 7 months ago
by
oliviermills