gghf
gghfez
AI & ML interests
Datasets, Linguistics
Organizations
None yet
gghfez's activity
Control vector discussion
396
#2 opened 3 months ago
by
ChuckMcSneed
quantized question
2
#2 opened 4 days ago
by
jokemodel1710
Add EXL2, INT8, and/or INT4 version of the model, PLEASE!
3
#21 opened 12 days ago
by
Abdelhak
Good stuff
6
#1 opened 11 days ago
by
BigHuggyD
how
1
#1 opened 23 days ago
by
schnapper79
Usage
14
#6 opened 19 days ago
by
schnapper79
Model suggestions and requests
15
#5 opened 22 days ago
by
jukofyork
hilarious model card
#9 opened 18 days ago
by
gghfez
These seem to work with finetunes too
19
#3 opened about 1 month ago
by
gghfez
Feedback
33
#3 opened about 1 month ago
by
ChuckMcSneed
"RPMax's Unconventional Approach"
35
#1 opened 26 days ago
by
jukofyork
q8 gives error in LM studio: "Checksum failed file corrupted"
3
#1 opened about 1 month ago
by
tazztone
Difference between this model and the one Meta released
3
#1 opened about 2 months ago
by
deleted
Feedback
10
#1 opened about 1 month ago
by
TheDrummer
How did you do this?
11
#1 opened about 1 month ago
by
jukofyork
A very quick test using wizard-lm-2:8x22b and temperature = 0
18
#1 opened about 1 month ago
by
jukofyork
How to efficiently use this model?
2
#3 opened about 1 month ago
by
Varkoyote
Consider a mistral-7b-instruct-v0.3 to use as an exl2 draft model with this?
4
#3 opened about 2 months ago
by
gghfez
Praise and Criticism
8
#23 opened about 2 months ago
by
ChuckMcSneed
How to create gguf fromm this
5
#3 opened about 2 months ago
by
DerErnst
difference
3
#1 opened 3 months ago
by
ehartford
Where GGUF?
7
#1 opened 2 months ago
by
rdtfddgrffdgfdghfghdfujgdhgsf
max_position_embeddings update in config.json
3
#2 opened 2 months ago
by
Inktomi93
Can't load in LM studio
10
#1 opened 3 months ago
by
YujiKaido
Example groupchat-friendly character cards?
#1 opened 3 months ago
by
gghfez
GGUF (Q4_K_M only) outputs gibberish
15
#3 opened 4 months ago
by
Ainonake
can someone make an EXL2 models for this but not using the max length 2048 thing :(
3
#7 opened 4 months ago
by
NimbleDreams
Quite disappointed with your decision to re-upload.
17
#2 opened 4 months ago
by
JosephusCheung
ValueError: ## Could not find lm_head.* in model
3
#1 opened 4 months ago
by
Asdfgbvcxz3355
exl2
3
#1 opened 4 months ago
by
DmitryPLSKN
Congrats!
15
#1 opened 4 months ago
by
aaronday3
did you have to do anything special to quantize this one?
1
#1 opened 5 months ago
by
gghfez
It works, and IMO, it actually feels safter than the judgemental refusals.
2
#5 opened 5 months ago
by
gghfez
Better way to download particular versions and track progress
3
#4 opened 6 months ago
by
hrishbhdalal
Any chance of a 3.75bpw?
5
#3 opened 6 months ago
by
gghfez
Cutoff March, 2023? Shouldn't it be 2024?
2
#7 opened 6 months ago
by
kil3r
That wizardlm 8x22b is very advanced.!
18
#8 opened 6 months ago
by
mirek190
Repetitive Text
13
#8 opened 10 months ago
by
mlenno1
Reasoning this model id worse that original mixtral-8x7b-instruct model.
2
#4 opened 10 months ago
by
mirek190
🚩 Report: Not working
7
#54 opened 10 months ago
by
Sksis
Links for sample inference and database schema are dead
11
#4 opened 11 months ago
by
NPap