DAN™
dranger003
AI & ML interests
None yet
Organizations
None yet
dranger003's activity
Update README.md with license information
#1 opened 6 days ago
by
Chen-01AI
Update README.md with license information
#1 opened 6 days ago
by
Chen-01AI
Update README.md with license information
#1 opened 6 days ago
by
Chen-01AI
Update README.md with license information
#2 opened 8 days ago
by
Chen-01AI
How to enable streaming for phi 3 vision model ?
6
#15 opened about 1 month ago
by
bhimrazy
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1668241569727-636f533c1ca0ea5107ed171d.png)
I'm generating a imatrix using `groups_merged.txt` if you want me to run any tests?
19
#15 opened 3 months ago
by
jukofyork
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65995c45539c808e84c38bf1/FiU-p4LC6Ar0G2_1stO8d.png)
Is the KV cache of these models unusually high?
1
#6 opened about 1 month ago
by
Hugsanir
How about a quantized version that fits in 16 GB of memory like wizardlm?
3
#19 opened about 2 months ago
by
Zibri
Update chat templates
2
#5 opened 3 months ago
by
CISCai
Will you redo quants after your bpe pr gets merged?
2
#18 opened 2 months ago
by
ggnoy
can't use llama load gguf model
2
#6 opened 2 months ago
by
Tianyi000
35B-beta is realeased
4
#3 opened 2 months ago
by
tastypear
Update chat templates
6
#17 opened 3 months ago
by
CISCai
ollama failed to create model
3
#3 opened 3 months ago
by
edisonzf2020
Can't merge files with gguf
7
#16 opened 3 months ago
by
zedmango
is it possible to use this model with LM Studio ??
2
#1 opened 3 months ago
by
michabbb
Can we get a Q4 without the IMat?
2
#14 opened 3 months ago
by
yehiaserag
Reuse your `ggml-dbrx-instruct-16x12b-q8_0-imatrix.dat` file?
20
#1 opened 3 months ago
by
jukofyork
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65995c45539c808e84c38bf1/FiU-p4LC6Ar0G2_1stO8d.png)
prompt eval too slow
2
#4 opened 3 months ago
by
lfjmgs
Very sensitve to any repetition penalty!
2
#2 opened 3 months ago
by
jukofyork
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65995c45539c808e84c38bf1/FiU-p4LC6Ar0G2_1stO8d.png)
can you guys share the size & perlexity tables thanks
1
#3 opened 3 months ago
by
habout632
![](https://cdn-avatars.huggingface.co/v1/production/uploads/641ab64da63c4e80623188be/tepIlmiSYiCyKvsjYZGdC.png)
Garbled output in llama.cpp
2
#13 opened 3 months ago
by
spanielrassler
fail on 104b-iq2_xxs.gguf with llama.cpp
4
#12 opened 3 months ago
by
telehan
PR #5796 is merged
1
#1 opened 3 months ago
by
Joseph717171
Invalid split files?
3
#11 opened 3 months ago
by
SabinStargem
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/TKk0SYTJxvCYG3tZPpTQt.jpeg)
Unable to load in ollama built from PR branch
3
#10 opened 3 months ago
by
gigq
What does iMat mean?
15
#2 opened 3 months ago
by
AS1200
Is IQ1_S broken? If so why list it here?
1
#9 opened 3 months ago
by
stduhpf
Fast work by the people on the llama.cpp team
3
#8 opened 3 months ago
by
qaraleza
Add model sizes
1
#5 opened 3 months ago
by
nanoflooder
For a context of at least 32K tokens which version on a 2x16GB Gpu Config?
1
#3 opened 3 months ago
by
Kalemnor
iq3_xxs request
2
#1 opened 3 months ago
by
yamikumods
support by llama-cpp-python?
7
#2 opened 3 months ago
by
madhucharan
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1618583036392-noauth.jpeg)
5 quants?
5
#1 opened 4 months ago
by
Orenguteng
![](https://cdn-avatars.huggingface.co/v1/production/uploads/644ad182f434a6a63b18eee6/3h-CHOLHa_r4pUpgO7Trf.png)
Bigger quants
1
#1 opened 3 months ago
by
WeirdObs
Thanks for your quants!
9
#2 opened 3 months ago
by
Cran-May
About q4_k and q5_k
1
#2 opened 3 months ago
by
stduhpf
How did you convert it?
3
#2 opened 3 months ago
by
froggeric
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65a681d3da9f6df1410562e9/WEM0smEQq8os99cMSmnoq.png)
Can't download via text gen web ui
1
#2 opened 3 months ago
by
AS1200
May the 2-bit compression still face some performance limitations.
2
#1 opened 4 months ago
by
DesperateZero
Cannot load model due to invalid format
2
#1 opened 4 months ago
by
ABX-AI
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65d936ad52eca001fdcd3245/aNb_Q3IdfGDmlS3cRzOEw.png)
More quant types
5
#2 opened 4 months ago
by
Wubbbi
Add quants for Q5
1
#2 opened 4 months ago
by
dzupin
New and improved Q1_S quants
2
#1 opened 4 months ago
by
LapinMalin
imatrix problem
3
#1 opened 4 months ago
by
DataSoul
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64b3eb9b93679cd0094dc95d/eBX-78aOs6cVencjM-3ME.png)
corrupt download or bad file?
2
#1 opened 4 months ago
by
Terminus-26
Tokens overrides (added_tokens_decoder)
2
#1 opened 4 months ago
by
dranger003
What is going on with this model?
1
#1 opened 4 months ago
by
MrVolk
Tokenizer issues?
2
#3 opened 4 months ago
by
xhyi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1630460859893-612b2b983394ed91a3c6ea2a.jpeg)
Could you please provide GGUF Files? :)
2
#1 opened 4 months ago
by
Venkman42
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6493317e9621f988db6c469c/qoxbdTDi-Pouyjq4MwiAG.png)
How did you make these quants?
5
#1 opened 4 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
Q4_k_s version please
1
#2 opened 5 months ago
by
Hoioi
a few interesting models
5
#1 opened 4 months ago
by
KnutJaegersberg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1669551186189-63732ebbbd81fae2b3aaf3fb.jpeg)
Quantisation parameters + Q5_K_M version?
2
#1 opened 4 months ago
by
smcleod
![](https://cdn-avatars.huggingface.co/v1/production/uploads/630fff3f02ce39336c495fe9/CZmQtRB4eGVbRBYT3_IH3.png)
Any chance of providing an iMatrix?
2
#2 opened 4 months ago
by
smcleod
![](https://cdn-avatars.huggingface.co/v1/production/uploads/630fff3f02ce39336c495fe9/CZmQtRB4eGVbRBYT3_IH3.png)
Slow prompt processing
2
#2 opened 5 months ago
by
OrangeApples
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/6rJmMwNSqswKhvckak5vn.jpeg)
A request for quantization.
3
#1 opened 5 months ago
by
Kotokin
iMatrix, IQ2_XS & IQ2_XXS
13
#2 opened 5 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
A request for quantization.
1
#1 opened 5 months ago
by
Kotokin