brucethemoose
brucethemoose
AI & ML interests
Stable Diffusion, Upscaling, Video Processing
Organizations
brucethemoose's activity
Adding Evaluation Results
#3 opened 6 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
New activity in
brucethemoose/CaPlatTessDolXaBoros-Yi-34B-200K-DARE-Ties-ExtremeDensity
6 months ago
Adding Evaluation Results
#1 opened 6 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#4 opened 6 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#2 opened 6 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Adding Evaluation Results
#3 opened 6 months ago
by
leaderboard-pr-bot
![](https://cdn-avatars.huggingface.co/v1/production/uploads/655506df9dc61e22c5f9c732/IZGvup0FdVlioPPIPnzZv.jpeg)
Positivity Bias?
2
#7 opened 6 months ago
by
Sergal222
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/tUyEwNY8cwXgwQX1Zv_Aj.jpeg)
Yi 34b 200k context update, will there be an updated version of this one?
4
#9 opened 6 months ago
by
Olafangensan
Weight updates?
8
#13 opened 6 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Just wanted to say thank you.
2
#8 opened 6 months ago
by
MB7977
Some notes on the models used.
13
#1 opened 7 months ago
by
ParasiticRogue
![](https://cdn-avatars.huggingface.co/v1/production/uploads/657ac4daf10a984150b1a679/ynZtPbuL3bUC73eC3k70e.png)
Gemma evaluation?
1
#4 opened 6 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Can i get a tldr of what exactly "imatrix quantization" is?
1
#1 opened 6 months ago
by
IZA09
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6578b52aee40482b5c50695c/Kayi_ChAfvWurNq89xNQ7.png)
Chat format?
1
#1 opened 6 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
tokenizer.model failing to load
2
#2 opened 6 months ago
by
tylerdev
Upload tokenizer.model for quantization
2
#5 opened 6 months ago
by
GusPuffy
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/x183WRJn2-3O8x9OQTXeV.jpeg)
ExLlamav2_HF load model -> ValueError: ## Could not find lm_head.* in model
2
#1 opened 7 months ago
by
HendrikW80
Smaller quant for 16GB?
3
#1 opened 7 months ago
by
zappa2005
GGUF version please
17
#3 opened 7 months ago
by
Hoioi
Possibly my new favourite roleplaying model!
12
#2 opened 7 months ago
by
MarinaraSpaghetti
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6550b16f7490049d6237f200/V19vjfHks2FARNyzVSKhi.jpeg)
Is there documentation for quantization alignment in long text?
2
#4 opened 7 months ago
by
Trangle
Low perplexity!
1
#1 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
34b models tests
7
#1 opened 7 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
Model "TriadParty/deepmoney-34b-200k-chat-evaluator" was not found on hub!
4
#4 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Instruct Formatting
2
#3 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Some benchs
4
#2 opened 7 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
What is this?
6
#1 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Tokenizer of Yi Dare v5
8
#4 opened 7 months ago
by
Nexesenex
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6451b24dc5d273f95482bfa4/YFUHCkSsz8vkYb9buv9GT.jpeg)
Have you considered revisiting another pure Vicuna merge using nontoxic-bagel?
28
#1 opened 8 months ago
by
ParasiticRogue
![](https://cdn-avatars.huggingface.co/v1/production/uploads/657ac4daf10a984150b1a679/ynZtPbuL3bUC73eC3k70e.png)
Llama Compatibility
3
#1 opened 7 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Smaller quant
12
#1 opened 7 months ago
by
zappa2005
Training data language?
4
#4 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Awesome model! Training parameters?
6
#1 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
No tokenizer.model???
6
#1 opened 8 months ago
by
wyxwangmed
Awesome!
2
#2 opened 8 months ago
by
traveltube
Did you upload the wrong model.safetensors.index.json?
1
#1 opened 8 months ago
by
Labmem009
configs do not match tokenizer vocab size
2
#5 opened 8 months ago
by
carson-together
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64c7f044b8685df8002113e3/kJGvyJiUmIb2ZVrxH8sHJ.jpeg)
200K Version?
3
#3 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
settings
5
#3 opened 8 months ago
by
Steelskull
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64545af5ec40bbbd01242ca6/D0Nd7GHjqZNmIksQFRSGz.png)
How did you fix Nous hermes 2?
#1 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Nice model!
4
#1 opened 8 months ago
by
acrastt
Context Length?
4
#1 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Model sometimes replies to older msgs in context as if it's the most recent msg
1
#1 opened 8 months ago
by
ReMeDy-TV
![](https://cdn-avatars.huggingface.co/v1/production/uploads/640590b591ee7d7f287183ae/PQefPEgtaNqnTNfumrZXr.jpeg)
Broken Model
23
#2 opened 9 months ago
by
Nycoorias
200K Version?
2
#1 opened 8 months ago
by
brucethemoose
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1670003187019-noauth.png)
Model evaluation failed
3
#494 opened 8 months ago
by
adamo1139
Leaderboard evaluation failed.
3
#3 opened 8 months ago
by
adamo1139
Request for separate Leaderboard for Merged Models
21
#473 opened 8 months ago
by
ajibawa-2023
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64aea8ff67511bd3d965697b/Jxn52EmDF5RApJh8antxn.jpeg)
bpw and corresponding vram usage
18
#1 opened 8 months ago
by
joujiboi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/631608b395b55e2621d033a8/hwcbRiLms6AyzUhGIx-fC.png)
The model often answers the question over and over again with no overflow of video memory
1
#2 opened 8 months ago
by
xldistance
exllamav2 quant?
3
#1 opened 8 months ago
by
traveltube
4090 Graphics Card 24gb Video Memory Not Enough
2
#2 opened 8 months ago
by
xldistance