Akarshan Biswas
qnixsynapse
AI & ML interests
NLP, models, quantization
Recent Activity
liked a model 4 days ago
Qwen/Qwen3.5-9B updated a model 2 months ago
qnixsynapse/gemma-3n-E4B-it-IQ4_XS-GGUF published a model 2 months ago
qnixsynapse/gemma-3n-E4B-it-IQ4_XS-GGUFOrganizations
None yet
Invalid version/backend format: none. Expected format: <version>/<backend>
1
#1 opened 7 months ago
by
pligus
Add "Image-Text-to-Text" label to gemma-3-12B
2
#2 opened 10 months ago
by
qnixsynapse
Add "Image-Text-to-Text" label to Gemma-3-27B
#3 opened 10 months ago
by
qnixsynapse
Add "Image-Text-to-Text" label to Gemma 3 4B
#1 opened 10 months ago
by
qnixsynapse
Tool calling support in Gemma 2
2
#50 opened over 1 year ago
by
qnixsynapse
[MODELS] Discussion
β€οΈπ 38
800
#372 opened about 2 years ago
by
victor
[TOOLS] Community Discussion
ππ₯ 3
27
#455 opened almost 2 years ago
by
victor
Wrong number of tensors; expected 292, got 291
6
#69 opened over 1 year ago
by
KingBadger
[FEATURE] Tools
β€οΈπ₯ 78
69
#470 opened almost 2 years ago
by
victor
Utterly based
ππ 8
1
#9 opened over 1 year ago
by
llama-anon
Add IQ Quantization support with the help of imatrix and GPUs
π 6
8
#35 opened almost 2 years ago
by
qnixsynapse
Suggestion: Host Gemma2 using keras_nlp instead of transformers library for the time being
2
#498 opened over 1 year ago
by
qnixsynapse
The best 8B in the planet right now. PERIOD!
2
#22 opened almost 2 years ago
by
cyberneticos
How many active parameters does this model have?
3
#6 opened almost 2 years ago
by
lewtun
7B or 8B?
4
#24 opened about 2 years ago
by
amgadhasan
Which model is responsible for naming of the thread?
8
#402 opened almost 2 years ago
by
qnixsynapse
Number of parameters
8
#9 opened almost 2 years ago
by
HugoLaurencon
Loading the model
3
#3 opened over 2 years ago
by
PyrroAiakid
Looking for GGUF format for this model
1
#14 opened over 2 years ago
by
barha
Help needed to load model
π 4
19
#13 opened over 2 years ago
by
sanjay-dev-ds-28