xzuyn
xzuyn
AI & ML interests
Doing stuff related to KoboldCPP
Organizations
xzuyn's activity
I thought 21B is a placebo? Is it?
2
#1 opened about 2 months ago
by
UniversalLove333
chat_template seems like it was converted incorrectly.
5
#10 opened 2 months ago
by
xzuyn
Why is `multi_obj_rewards` multipled by 5, but then 0.5 is subtracted from it?
2
#11 opened 2 months ago
by
xzuyn
https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO
1
#155 opened 2 months ago
by
xzuyn
I used your set on LLaMa-3-Instruct-8B 🙂
#3 opened 2 months ago
by
xzuyn
Interesting stuff you got here.
1
#2 opened 3 months ago
by
cubestarx
Notebook seems to have issues with the template.
#2 opened 3 months ago
by
xzuyn
Amazing model
1
#1 opened 3 months ago
by
itsnottme
Always outputs 47 second wav even if set to less
1
#6 opened 4 months ago
by
xzuyn
Interesting model
1
#1 opened 4 months ago
by
Utochi
https://huggingface.co/PJMixers/LLaMa-3-CursedStock-v1.6-8B
1
#66 opened 4 months ago
by
xzuyn
How does this compare to SystemChat-1.1?
1
#2 opened 4 months ago
by
xzuyn
Doesn't create a tree for some pages
4
#2 opened 4 months ago
by
xzuyn
Add more models
1
#1 opened 4 months ago
by
xzuyn
Update README.md & mergekit_config.yml
#5 opened 4 months ago
by
xzuyn
What is going on with your vocab?
3
#10 opened 4 months ago
by
xzuyn
Adding `safetensors` variant of this model
#1 opened 4 months ago
by
SFconvertbot
Question about added tokens
3
#7 opened 5 months ago
by
xzuyn
What is 256k?
16
#1 opened 5 months ago
by
supercharge19
Needle-in-a-Haystack
#3 opened 5 months ago
by
xzuyn
Add dataset to model card
#2 opened 5 months ago
by
xzuyn
Update post-processor to add bos
5
#41 opened 5 months ago
by
pcuenq
License?
2
#2 opened 5 months ago
by
choco9966
Fix example usage code
#4 opened 5 months ago
by
xzuyn
Replace links with ones from Wayback Machine
#2 opened 5 months ago
by
xzuyn
`enhanced_instruction` contains the `response`
10
#2 opened 5 months ago
by
xzuyn
Was this model based of Mistral-7B-v0.2 from the start?
4
#72 opened 6 months ago
by
stduhpf
Grammar issues in system prompts.
1
#6 opened 6 months ago
by
xzuyn
Thanks for the set.
#2 opened 8 months ago
by
xzuyn
[bot] Conversion to Parquet
#1 opened 8 months ago
by
parquet-converter
What format is the jpg_0 & jpg_1?
3
#2 opened 9 months ago
by
xzuyn
love the model but it's a duplicate on the 7b leaderboard
1
#1 opened 10 months ago
by
nisten
How does this compare to the finetuned-lj model?
1
#4 opened 11 months ago
by
xzuyn
Can we get safetensors versions?
9
#1 opened over 1 year ago
by
xzuyn
How does `data_extra_filtered` differ from `data`?
#2 opened 11 months ago
by
xzuyn
Models with multiple submissions.
5
#322 opened 11 months ago
by
xzuyn
Is `added_tokens.json` intended to be here?
4
#43 opened 12 months ago
by
xzuyn
Dataset quality seems quite poor.
#1 opened 12 months ago
by
xzuyn
Apologies. Incorrect repo.
#1 opened 12 months ago
by
xzuyn
Merging Adapter.
#5 opened 12 months ago
by
xzuyn
`Running Evaluation Queue` seems to have gotten stuck on a model.
2
#268 opened about 1 year ago
by
xzuyn
WizardLM 30B model seems to rank way lower then it probably should be at.
4
#266 opened about 1 year ago
by
felixz
Please remove these models of mine from the leaderboard.
4
#250 opened about 1 year ago
by
xzuyn
Runtime error on CPU UPGRADE
2
#244 opened about 1 year ago
by
xzuyn
Can't submit QLoRA for eval because `Base model "meta-llama/Llama-2-7b-hf" was not found on hub!`
1
#241 opened about 1 year ago
by
xzuyn
Model failure.
1
#240 opened about 1 year ago
by
xzuyn
add box which shows encoded tokens, also add labels
#1 opened about 1 year ago
by
xzuyn
Can you upload a version which only uses the subset for Tulu?
2
#1 opened about 1 year ago
by
xzuyn
Could you please make this model?
2
#1 opened about 1 year ago
by
Hoioi
Adding `safetensors` variant of this model
#2 opened about 1 year ago
by
xzuyn
Adding `safetensors` variant of this model
#1 opened about 1 year ago
by
xzuyn
Could we get original weights for this?
#4 opened about 1 year ago
by
xzuyn
Adding `safetensors` variant of this model
#1 opened about 1 year ago
by
SFconvertbot
Adding `safetensors` variant of this model
#1 opened about 1 year ago
by
SFconvertbot
Prompt format?
1
#3 opened about 1 year ago
by
iamrobotbear
how should i use this model?
1
#1 opened over 1 year ago
by
dashuxu
Prompt Format?
2
#4 opened over 1 year ago
by
xzuyn
Prompt Format.
3
#1 opened over 1 year ago
by
xzuyn
Question on alpaca format training.
1
#1 opened over 1 year ago
by
xzuyn