Francisco
Panchovix
AI & ML interests
ML, Text2Image models, Large Language Models.
Organizations
Panchovix's activity
Any chance for a 6bpw one?
#3 opened 5 months ago
by
Panchovix
unquantized weights?
1
#8 opened 5 months ago
by
narutofan125
Example code on running the model?
2
#7 opened 6 months ago
by
bwzimpel
3bpw spam random words on default settings with oobabooga
4
#2 opened 6 months ago
by
sergkisel3v
Should we expect a version for GGUF?
2
#6 opened 6 months ago
by
AS1200
Quantitative command?
7
#4 opened 6 months ago
by
akoyaki
Quantization update?
3
#5 opened 6 months ago
by
imi2
GGUF format?
3
#3 opened 7 months ago
by
Puchacz19
EXL2 Quants
2
#2 opened 7 months ago
by
OrangeApples
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/6rJmMwNSqswKhvckak5vn.jpeg)
Summoning EXL2 version ;)
9
#2 opened 7 months ago
by
wolfram
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6303ca537373aacccd85d8a7/JZqLjXZVGWXJdWUNI99db.jpeg)
Calibration dataset?
3
#1 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Possible to rpcal a GGUF version?
4
#1 opened 7 months ago
by
PathosOnSunday
Nice work! Which dataset did you use for measurement.json?
4
#2 opened 7 months ago
by
Panchovix
Any chance for an EXL2 version?
15
#2 opened 7 months ago
by
wolfram
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6303ca537373aacccd85d8a7/JZqLjXZVGWXJdWUNI99db.jpeg)
VRAM requirements
2
#2 opened 8 months ago
by
practical-dreamer
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642e4fbda0b65dce1f875e90/o08Ni4hSRiqyoBy6MEg-a.jpeg)
Adding Evaluation Results
#1 opened 7 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#2 opened 7 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
3bpw not working anymore
6
#1 opened 8 months ago
by
mpasila
Upload xwin_wizardlm-evol-70k_measurement.json
1
#1 opened 9 months ago
by
sophosympatheia
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63b4b108103617b0a5b0f6f5/A5P1pKfMv5KhGvnpfo21G.png)
Can you please create a 3-bit file via exllama2?
1
#3 opened 9 months ago
by
Kotokin
Error parsing message when loading model
6
#2 opened 10 months ago
by
MasonJ
Update bin2safetensors/convert.py
#2 opened 10 months ago
by
Thireus
Error while loading
2
#1 opened 10 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
Update bin2safetensors/convert.py
1
#1 opened 10 months ago
by
Thireus
Convertion process
3
#1 opened 10 months ago
by
Thireus
Does this finetune let you use 4096 context?
1
#2 opened 11 months ago
by
Panchovix
This model is not working
5
#1 opened 12 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
RuntimeError: unable to mmap 19426750144 bytes
3
#3 opened 12 months ago
by
Leaf45
Thanks for all the hard work! Chance to see superhot-65b?
9
#1 opened about 1 year ago
by
Panchovix
Best parameters for 24GB VRAM?
1
#2 opened about 1 year ago
by
Thireus
Prompt format?
1
#1 opened about 1 year ago
by
Thireus
Prompt format?
1
#1 opened about 1 year ago
by
Thireus
Upload 4 files
#1 opened about 1 year ago
by
Panchovix
Can you be more specific how to use 8k context with ExLLama in Oobabooga?
4
#3 opened about 1 year ago
by
justsumguy
Is possible to see a merged Airoboros-33b-SuperHOT-8k without GPTQ?
1
#1 opened about 1 year ago
by
Panchovix