Bartowski
bartowski
AI & ML interests
None yet
Organizations
bartowski's activity
EOS token is getting printed
9
#1 opened 1 day ago
by
migtissera
Please check these quantizations.
1
#40 opened about 12 hours ago
by
ZeroWw
Testing experimental quants
2
#2 opened 1 day ago
by
bartowski
Error loading model
3
#1 opened 1 day ago
by
smchapman54
How did you convert it?
5
#1 opened 2 days ago
by
ZeroWw
Gibberish output
2
#1 opened 2 days ago
by
Adriato
Quantization suggestion
24
#3 opened 6 days ago
by
ZeroWw
-cml / --chatml has been discontinued in llama.cpp
2
#1 opened 12 days ago
by
algorithm
Please post f16 quantization.
3
#1 opened 27 days ago
by
ZeroWw
Error when trying to run in OobaBooga
5
#1 opened 5 days ago
by
AIGUYCONTENT
BOS token discussion
25
#2 opened 13 days ago
by
woofwolfy
Big jump between IQ2_XXS and IQ2_M - any chance of IQ2_XS quants?
2
#1 opened 5 days ago
by
smcleod
Gguf?
4
#1 opened 6 days ago
by
edwardDali
Requant Request
2
#1 opened 8 days ago
by
leonardlin
Update config.json
1
#36 opened 10 days ago
by
rameshjhar480
prompt format and text-gen
8
#1 opened 13 days ago
by
gandolfi
blocky blocky blocky
3
#1 opened 12 days ago
by
mclassHF2023
Loading AutoTokenizer and AutoModelForCausalLM
4
#3 opened 12 days ago
by
nramirezuy
Add base_model
7
#2 opened 14 days ago
by
julien-c
Getting gibberish responses
2
#1 opened 12 days ago
by
jaycann2
bos_token==pad token??
2
#3 opened 12 days ago
by
Jerry-hyl
Issue with q8_0
10
#1 opened 12 days ago
by
smchapman54
Upload ONNX weights
1
#1 opened 12 days ago
by
Xenova
Great model. FP16 request
3
#1 opened 13 days ago
by
Languido
DON'T EVEN BOTHER APPLYING - Unofficial ZeroGPU Policy Decoded
43
#69 opened 14 days ago
by
JosephusCheung
Good model but Bullshit chart and inaccurate numbers
32
#20 opened about 2 months ago
by
rombodawg
Could you make a exl2 quant for the weighted/imatrix version?
3
#1 opened 15 days ago
by
mjh657
Normally i would say thank you for quanting.
7
#1 opened 16 days ago
by
Nitral-AI
Prompt format
9
#1 opened 20 days ago
by
supportend
not able to load with llamacpp-python
1
#1 opened 16 days ago
by
balu548411
"This model also supports the following FIM tokens"
5
#1 opened 19 days ago
by
catarino
pytorch_model files only 33MB?
1
#1 opened 19 days ago
by
bartowski
Update tokenizer to include [SUFFIX] and [PREFIX] tokens?
1
#1 opened 19 days ago
by
ShiveringSpine
Update README.md
2
#1 opened 20 days ago
by
fblgit
Can't load model in LlamaCpp
7
#4 opened 21 days ago
by
ThoilGoyang
exl2 vs GGUF at 8bit
1
#2 opened 21 days ago
by
Samvanity
On some promts, medium is worse than mini&small?
6
#2 opened 26 days ago
by
urtuuuu
core dumps when attempting falcon-11B-Q6_K.gguf
1
#1 opened 23 days ago
by
LaferriereJC
It seems the quants were created before the BPE pre-tokenizer fix?
1
#1 opened 23 days ago
by
skruse
More quantization variants
11
#1 opened about 1 month ago
by
Yuma42
Promt format question
2
#1 opened 23 days ago
by
urtuuuu
Chat template
#4 opened 24 days ago
by
bartowski
gguf model
2
#2 opened 25 days ago
by
edwardDali
Seems can not use response_format in llama-cpp-python
1
#3 opened 25 days ago
by
svjack
Why does it generate nothing but garbage?
4
#1 opened 25 days ago
by
newsletter
Another <EOS_TOKEN> issue
1
#2 opened 25 days ago
by
alexcardo
Q1 Model
4
#1 opened 26 days ago
by
neelkalpa
Update README.md
2
#1 opened 26 days ago
by
Joseph717171
I think this is actually just 0.1
3
#1 opened 26 days ago
by
bartowski
no system message?
8
#14 opened 26 days ago
by
mclassHF2023
v3 tokenizer
5
#1 opened 27 days ago
by
ayyylol
Add quant links
#7 opened 28 days ago
by
bartowski
Chat template - use with Ollama?
2
#1 opened 29 days ago
by
smcleod
Context size?
2
#1 opened 29 days ago
by
dasChronos1
GGUF and exl2 quants for anyone who wants
3
#2 opened about 1 month ago
by
bartowski
OSError: [Errno 36] File name too long
4
#7 opened about 1 month ago
by
spoilvoid
Only Hallucinates
1
#3 opened about 1 month ago
by
LaughterOnWater