Hugging Face's logo

Meta Llama

Enterprise
company
Verified
https://ai.meta.com/llama/
meta-llama
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

wukaixingxp  new activity 11 days ago
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8:Quantizer: Running into an error with quantization "TypeError: 'dict' object is not callable"
richardzou5  new activity 11 days ago
meta-llama/Llama-4-Maverick-17B-128E-Instruct:torch compile compatibility issue
wukaixingxp  new activity 17 days ago
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8:Support for FP8 + Fused MoE layers in vLLM?
View all activity

meta-llama's activity

janghyuncho7 
authored 2 papers 8 days ago
wukaixingxp 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 11 days ago

Quantizer: Running into an error with quantization "TypeError: 'dict' object is not callable"

3
#24 opened 11 days ago by
AaronVogler
richardzou5 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct 11 days ago

torch compile compatibility issue

3
6
#23 opened 21 days ago by
jhmun
wukaixingxp 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 17 days ago

Support for FP8 + Fused MoE layers in vLLM?

2
#23 opened 18 days ago by
szlevi
Sanyam 
in meta-llama/Llama-4-Scout-17B-16E 18 days ago

Model does not load evenly on all available GPUs device_map= auto leading to OOM

2
#34 opened 18 days ago by
sugunav14
pcuenq 
in meta-llama/Llama-4-Maverick-17B-128E 19 days ago

remove <|finetune_right_pad_id|> and change pad_token to <|finetune_right_pad|>

1
#16 opened 20 days ago by
wukaixingxp

change pad_token to <|finetune_right_pad|>
#15 opened 20 days ago by
wukaixingxp
pcuenq 
in meta-llama/Llama-4-Scout-17B-16E 19 days ago

Fixed the model id in the snippet.

1
#22 opened 22 days ago by
mahmutc
pcuenq 
in meta-llama/Llama-4-Scout-17B-16E-Instruct 19 days ago

Update tokenizer

2
#43 opened 20 days ago by
pcuenq
pcuenq 
in meta-llama/Llama-4-Scout-17B-16E 19 days ago

change pad_token to <|finetune_right_pad|>
#29 opened 20 days ago by
wukaixingxp

remove <|finetune_right_pad_id|> and change pad_token to <|finetune_right_pad|>
#28 opened 20 days ago by
wukaixingxp
pcuenq 
in meta-llama/Llama-4-Scout-17B-16E-Instruct 19 days ago

remove <|finetune_right_pad_id|> and change pad_token to <|finetune_right_pad|>
#49 opened 20 days ago by
wukaixingxp

change pad_token to <|finetune_right_pad|>
#48 opened 20 days ago by
wukaixingxp
pcuenq 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 19 days ago

change pad_token to <|finetune_right_pad|>
#21 opened 20 days ago by
wukaixingxp

remove <|finetune_right_pad_id|> and change pad_token to <|finetune_right_pad|>
#20 opened 20 days ago by
wukaixingxp
pcuenq 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct 19 days ago

change pad_token to <|finetune_right_pad|>

4
#26 opened 21 days ago by
wukaixingxp
reach-vb 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 19 days ago

Update tag!
#22 opened 19 days ago by
reach-vb
reach-vb 
in meta-llama/Llama-4-Maverick-17B-128E-Instruct 19 days ago

Update tag!
#29 opened 19 days ago by
reach-vb
reach-vb 
in meta-llama/Llama-4-Scout-17B-16E 19 days ago

Update tag!
#31 opened 19 days ago by
reach-vb