Annuvin/YuE-s1-7B-anneal-en-cot-8.0bpw-h8-exl2
Updated
•
27
•
1
elinas
elinas
AI & ML interests
LLMs & Finetuning
Recent Activity
liked
a model
7 days ago
Annuvin/YuE-s1-7B-anneal-en-cot-8.0bpw-h8-exl2
new activity
8 days ago
elinas/Chronos-Gold-12B-1.0:system_prompt
updated
a model
4 months ago
ZeusLabs/Chronos-Platinum-72B
Organizations
elinas's activity
liked
a
model
7 days ago
system_prompt
2
#7 opened 17 days ago
by
Gruenie
updated
a
model
4 months ago
Really really good!
1
#3 opened 4 months ago
by
FiditeNemini
updated
a
collection
4 months ago
can you release the exl quant version?
2
#2 opened 5 months ago
by
zypcastles
liked
a
model
4 months ago
Qwen 2_5 32b?
2
#1 opened 5 months ago
by
DazzlingXeno
liked
a
model
5 months ago
This looks so good.
2
#2 opened 5 months ago
by
Kquant03
updated
2
models
5 months ago
Adding Evaluation Results
#6 opened 5 months ago
by
leaderboard-pr-bot
posted
an
update
5 months ago
Post
2324
We conducted an experiment in an effort to revive LLaMA 1 33B as it had unique prose and a lack of "GPT-isms" and "slop" in its pretraining data, as well as being one of the favorites at the time. With multiple finetune runs, we were able to extend the model from it's pretrained base of 2048 to ~12,000 tokens adding approx. 500M tokens in the process. The effective length is 16,384 but it's better to keep it on the lower range. It writes well and in multiple formats. In the future, we have some ideas like implementing GQA. Please take a look and we would love to hear your feedback!
ZeusLabs/Chronos-Divergence-33B
ZeusLabs/Chronos-Divergence-33B
liked
a
model
5 months ago
updated
a
model
5 months ago
updated
a
collection
5 months ago
updated
a
Space
5 months ago
Upload tokenizer.json
#2 opened 5 months ago
by
Suparious
updated
a
model
5 months ago