Yatharth Sharma
YaTharThShaRma999
AI & ML interests
None yet
Organizations
None yet
YaTharThShaRma999's activity
Quality compared to pixart alpha/sigma and hyper sd?
#1 opened 7 days ago
by
YaTharThShaRma999
Performance Degredation After Weight Update
4
#18 opened 11 days ago
by
evilperson068
Is this a model similar to hyper SD? Can it run in the same way
2
#2 opened 12 days ago
by
guicen
What is going on with your vocab?
2
#10 opened 10 days ago
by
xzuyn
Feedback
1
#31 opened 13 days ago
by
YaTharThShaRma999
Parameters and what lora?
1
#1 opened 13 days ago
by
YaTharThShaRma999
Trying to use llama-2-7b-chat.Q4_K_M.gguf with/without tensorflow weights
1
#33 opened 18 days ago
by
cgthayer
Love the project, when will CFG hyper-sd come?
11
#24 opened 20 days ago
by
brandostrong
I believe this might be a pretrained model?
1
#4 opened 30 days ago
by
ccibeekeoc42
Reducing Latency in Locally Hosted model
1
#8 opened 23 days ago
by
anshulchandel
Question about quality
1
#4 opened 27 days ago
by
YaTharThShaRma999
invalid magic number 00000000
8
#1 opened 8 months ago
by
BigDeeper
Waiting for Meta-Llama-3-8B-Instruct-gguf
1
#29 opened 30 days ago
by
anuragrawal
How do you estimate the number of GPUs required to run this model?
1
#29 opened about 1 month ago
by
vishjoshi
What are the diffences of this with Qwen/CodeQwen1.5-7B
6
#5 opened about 1 month ago
by
Kalemnor
Model is paraphrasing text instead of citing it verbatim
3
#7 opened about 1 month ago
by
sszymczyk
Quantization for more than 8 bits?
3
#25 opened about 1 month ago
by
ibalampanis
Very slow response on LM Studio with these settings
3
#4 opened about 1 month ago
by
yassersharaf
issue loading
1
#2 opened about 1 month ago
by
baelof
today's version of llama.cpp results in an error
9
#4 opened 5 months ago
by
LaferriereJC
Necessary material for llama2
7
#27 opened 10 months ago
by
Samitoo
No module Named Opitimum
1
#1 opened about 2 months ago
by
deeplearner123
hugging face version coming?
3
#2 opened 4 months ago
by
ctranslate2-4you
CUDA error - the provided PTX was compiled with an unsupported toolchain
12
#23 opened 7 months ago
by
melindmi
Unable to convert `llama-2-70b-chat.ggmlv3.q4_K_M.bin` to GGUF
2
#12 opened 9 months ago
by
barha
CUDA out of memory
18
#4 opened about 2 months ago
by
RedAISkye
Fix support for SGLang inference
11
#2 opened 3 months ago
by
aliencaocao
Trying to load on 8xA10 in 4 bit gives this error
5
#6 opened about 2 months ago
by
nbilla
llama-70b on the way?
1
#1 opened 2 months ago
by
GF110
Inference taking too much time
3
#9 opened 3 months ago
by
tariksetia
OSError: xai-org/grok-1 does not appear to have a file named config.json
1
#11 opened 2 months ago
by
emfhal
when the quantitative model will release? or does it support awq?
1
#20 opened 2 months ago
by
liuanping
314B params has 297G file size ?
3
#30 opened 2 months ago
by
DachengZhang
model size
1
#3 opened 2 months ago
by
HeHeYeast
Won't load into text gen ui with transformers
1
#3 opened 2 months ago
by
Turrican10
very slow inference speed
1
#1 opened 2 months ago
by
tunggad
How to reduce the loading time of pretrained model?
5
#40 opened 3 months ago
by
dylanbui
Base or Chat?
2
#1 opened 2 months ago
by
Neman
How to convert 4bit model back to fp16 data format?
3
#52 opened 2 months ago
by
tremblingbrain
Using Ctransformers for inference gives an error
8
#3 opened 7 months ago
by
ML610
Is there a working/quantized/exl2 (etc) version that will fit on a single 24GB video card (4090)
2
#170 opened 2 months ago
by
cleverest
Strange response
3
#3 opened 2 months ago
by
JoaoCP
how to deal with number of tokens exceeded maximum context length
2
#25 opened 2 months ago
by
Janmejay123
Enhance response time
3
#8 opened 3 months ago
by
Janmejay123
Model producing no output and running forever
3
#3 opened 3 months ago
by
rpeinl
Using Toppy as LLM for Skyrim NPC RP
3
#1 opened 3 months ago
by
Jdods84
Q6_K version is broken
7
#19 opened 5 months ago
by
tankstarwar
🚩 Report
1
#4 opened 3 months ago
by
dorito96
Does this work with CPU only?
1
#9 opened 3 months ago
by
borner
Help with llama-2-7b-chat.Q4_K_M.gguf already in local downloads
1
#23 opened 3 months ago
by
RaphaellG
Can I input a negative prompt to restrict the generation of certain bad things?
1
#8 opened 3 months ago
by
obtion
Running Llama-2-7B-32K-Instruct-GGML with llama.cpp ?
13
#1 opened 9 months ago
by
gsimard
Working example
6
#5 opened 3 months ago
by
hermanda
4 bit vs 8 bit
4
#2 opened 3 months ago
by
Doomed1986
About Sora
6
#8 opened 3 months ago
by
Fabrice-TIERCELIN
Not able to use with ctransformers
1
#12 opened 3 months ago
by
aravindsr
Why "llama-2-7b-chat.Q8_0.gguf" model is not recommended
3
#21 opened 3 months ago
by
AhmetOnur
Quantized Quality Bad?
1
#3 opened 3 months ago
by
thewise
Noobs's question
1
#1 opened 3 months ago
by
kekawia