arcee-ai
/

SuperNova-Medius

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (3)

This cross-architecture distillation, with Phi?

#14 opened 21 days ago by

sometimesanotion

Template

#13 opened 3 months ago by

Update SuperNova-Medius with a merge with Qwen/Qwen2.5-Coder-14B-Instruct + Further Training 😋

#12 opened 3 months ago by

max output tokens?

#11 opened 3 months ago by

Is there any example tutorial on mergekit-tokensurgeon?

#10 opened 3 months ago by

We distilled the logits of Llama 3.1 405B using an offline approach.

#9 opened 3 months ago by

Unusual tokenizer.json file size

#8 opened 3 months ago by

AuriAetherwiing

How about a 3 way merge with a distillation from Mistral Large? :D

#7 opened 3 months ago by

Ideal quantization levels

#6 opened 4 months ago by

Multilingual, Uncensored and extensive vocabulary.

#4 opened 4 months ago by

2 base models = a nice merge UI on the model page

#1 opened 4 months ago by