nvidia
/

Llama-3_3-Nemotron-Super-49B-v1_5

Text Generation

Model card Files Files and versions

Resources

View closed (1)

variable_cache.py compatibility for v4.57.2 / python3.12

#12 opened 6 days ago by

cannot import name 'NEED_SETUP_CACHE_CLASSES_MAPPING'

#11 opened 7 days ago by

Trying to fix issues with extra arguments to the model

#10 opened 18 days ago by

Since `transformers` v4.56.0` the dictionary `ALL_STATIC_CACHE_IMPLEMENTATIONS` replaced `NEED_SETUP_CACHE_CLASSES_MAPPING`

#9 opened 22 days ago by

Does vllm deployment supports --enable-reasoning and --reasoning-parser

#8 opened 2 months ago by

Possible to disable thinking via a karg?

#7 opened 3 months ago by

Cannot disable thinking mode

#5 opened 4 months ago by

Tool calling no stream

#4 opened 4 months ago by

FP8 Quants please

#3 opened 4 months ago by

there will be a nemotron ultra v1_5?

#2 opened 4 months ago by

Missing `modeling_decilm.py` when loading the model

#1 opened 4 months ago by