License compatibility
2
#17 opened about 2 months ago
by
Schilder
Improve language tag
#16 opened 4 months ago
by
lbourdois

Following the instructions
#15 opened 6 months ago
by
Markobes
This cross-architecture distillation, with Phi?
3
#14 opened 7 months ago
by
sometimesanotion

Template
1
#13 opened 10 months ago
by
isr431
Update SuperNova-Medius with a merge with Qwen/Qwen2.5-Coder-14B-Instruct + Further Training 😋
➕
2
11
#12 opened 10 months ago
by
Joseph717171
max output tokens?
1
#11 opened 10 months ago
by
sirus

Is there any example tutorial on mergekit-tokensurgeon?
#10 opened 10 months ago
by
win10

We distilled the logits of Llama 3.1 405B using an offline approach.
#9 opened 10 months ago
by
sirus

Unusual tokenizer.json file size
#8 opened 10 months ago
by
AuriAetherwiing

How about a 3 way merge with a distillation from Mistral Large? :D
❤️
1
#7 opened 10 months ago
by
DreamGenX

Ideal quantization levels
👍
1
2
#6 opened 10 months ago
by
jadbox
Multilingual, Uncensored and extensive vocabulary.
❤️
5
5
#4 opened 10 months ago
by
Kukedlc

2 base models = a nice merge UI on the model page
2
#1 opened 11 months ago
by
victor
