elinas
elinas
AI & ML interests
LLMs & Finetuning
Organizations
elinas's activity
Really really good!
1
#3 opened 19 days ago
by
FiditeNemini
can you release the exl quant version?
2
#2 opened 21 days ago
by
zypcastles
Qwen 2_5 32b?
2
#1 opened 22 days ago
by
DazzlingXeno
This looks so good.
2
#2 opened about 1 month ago
by
Kquant03
Adding Evaluation Results
#6 opened about 1 month ago
by
leaderboard-pr-bot
Upload tokenizer.json
#2 opened about 2 months ago
by
Suparious
no tokenizer.json?
2
#1 opened about 2 months ago
by
Suparious
Update safetensors index to point to .safetensors instead of .bin files
#4 opened about 2 months ago
by
ToastyPigeon
Context length plus feedback
3
#1 opened 2 months ago
by
MarinaraSpaghetti
Add safetensors
1
#3 opened 2 months ago
by
elinas
Update README.md
2
#1 opened 4 months ago
by
Steelskull
Add L3-Aethora-15B-V2 weights
#1 opened 4 months ago
by
elinas
Where is model File
1
#1 opened 6 months ago
by
KingNish
Adding Evaluation Results
#1 opened 6 months ago
by
leaderboard-pr-bot
Adding Evaluation Results
#3 opened 6 months ago
by
leaderboard-pr-bot
License update based on base model
#2 opened 7 months ago
by
elinas
Correct LICENSE, see details
#3 opened 7 months ago
by
elinas
Training code/script
#1 opened 12 months ago
by
elinas
Updated license detail from 'other' to 'llama2' for #hacktoberfest challenge.
1
#3 opened about 1 year ago
by
shreyashkar
7b model.
3
#2 opened about 1 year ago
by
Herman555
Was this trained on Llama 2 base or chat?
8
#1 opened about 1 year ago
by
IkariDev
7b model?
2
#1 opened about 1 year ago
by
Herman555
Dataset?
6
#1 opened over 1 year ago
by
flashvenom
patreon
2
#2 opened over 1 year ago
by
centurionrepository
With or w/o actor order?
1
#1 opened over 1 year ago
by
Yhyu13
Missing binaries?
1
#7 opened over 1 year ago
by
rikus2904
Compatible with transformers APIs?
1
#18 opened over 1 year ago
by
qiz
How to get this running on Oobabooga with RTX 4080 16GB?
8
#17 opened over 1 year ago
by
Goldenblood56
I'm getting 0.4 tokens/s on a 4090
2
#16 opened over 1 year ago
by
androtester
.pt version uses 2gb less VRAM for me than the non-groupsized .safetensors
3
#10 opened over 1 year ago
by
Monero
Chat interface
14
#11 opened over 1 year ago
by
rkj45
Could not find the quantized model in .pt or .safetensors format, exiting...
1
#14 opened over 1 year ago
by
donflopez
No longer works in OOba
12
#15 opened over 1 year ago
by
vdruts
Is not stopping after End Of answer, hallucinates the whole conversation
2
#2 opened over 1 year ago
by
underlines
Can't run the model
11
#1 opened over 1 year ago
by
MohamedRashad
Errors loading in OOba
5
#13 opened over 1 year ago
by
vdruts
Can you provide a notebook for testing alpaca-13b-lora-int4 ?
1
#6 opened over 1 year ago
by
murilocurti
Maximum new tokens size
5
#5 opened over 1 year ago
by
Fenfel
How to run?
1
#12 opened over 1 year ago
by
ColinS97
How is it different than other 4bit quants?
17
#1 opened over 1 year ago
by
yehiaserag
The new checkpoints performance comparasion
3
#8 opened over 1 year ago
by
Davidliudev
It doesn't work with the latest GPTQ-for-LLaMa
3
#4 opened over 1 year ago
by
BGLuck
Thank You For Sharing Your Model With Us!
#1 opened over 1 year ago
by
kagevazquez
How to do inferance?
9
#2 opened over 1 year ago
by
NePe
Thanks your hard work. Could you share your training hours with graphic card and vram info?
1
#6 opened over 1 year ago
by
wjjnova
Missing key(s) in state_dict
14
#2 opened over 1 year ago
by
athu16
Is this a LORA or full fine tune?
8
#2 opened over 1 year ago
by
teknium
Can't load your model
1
#1 opened over 1 year ago
by
leo-nid
oh you were the guy
6
#3 opened over 1 year ago
by
KnutJaegersberg
Is the lora built in to the model?
2
#3 opened over 1 year ago
by
Bikkies
Is this lora from chansung/alpaca-lora-30b?
1
#4 opened over 1 year ago
by
Yoshiii
Chat parameters - help
1
#5 opened over 1 year ago
by
Nondzu
3 epochs
3
#2 opened over 1 year ago
by
KnutJaegersberg
Create README.md
#1 opened over 1 year ago
by
elinas