nisten
nisten
AI & ML interests
boots & cats
Organizations
nisten's activity
Context Shift Problem
4
#4 opened 9 days ago
by
Vlad100
🚩 Report
17
#6 opened 11 days ago
by
gileneo
Reflection-Llama-3.1-70B was sonnet 3.5.
6
#5 opened 11 days ago
by
Enigrand
tokenizer and chat template fix for .gguf only
#9 opened 11 days ago
by
nisten
Third party evaluation on this so-called "LLM".
3
#7 opened 11 days ago
by
Enigrand
🚩 Report: Legal issue(s)
3
#8 opened 11 days ago
by
RDson
🚩 Report
4
#5 opened 11 days ago
by
gileneo
fixed chat template for reflection autoprompt
#3 opened 11 days ago
by
nisten
you might just have to edit the chat template in tokenizer_config.json
1
#1 opened 11 days ago
by
nisten
this good to convert to gguf without running LM_HEAD script?
1
#1 opened 11 days ago
by
nisten
[Cache Request] deepseek-ai/DeepSeek-V2-Chat-0628
#182 opened 24 days ago
by
nisten
[Cache Request] deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
#181 opened 24 days ago
by
nisten
Added Havana syndrome
#7 opened about 1 month ago
by
nisten
Added details for each disease generated by Gemini 1.5 Flash. Data is dirty and needs to be cleaned via removing notes etc.
1
#6 opened about 1 month ago
by
beratcmn
Added PCD and beta thalassemia
1
#5 opened about 1 month ago
by
mhdann
Added eosinophilic fasciitis and VEXAS
1
#1 opened about 1 month ago
by
cmcmaster
Standard definitions, diagnostic criteria, etc
1
#4 opened about 1 month ago
by
Jdkee
Upload 2 files
1
#2 opened about 1 month ago
by
nisten
Upload IMG_20240722_030306.jpg
1
#3 opened about 1 month ago
by
Moels
Upload IMG_20240722_030839.jpg
1
#4 opened about 1 month ago
by
Moels
Fix title
1
#1 opened about 2 months ago
by
informatiker
Can you post a log of how this model was created from the start?
2
#2 opened about 2 months ago
by
ZeroWw
Question about 1-bit quant
2
#2 opened about 2 months ago
by
ThomasBaruzier
Tried aria2 commands to download q1 version but got an error -- files appear to be missing
1
#1 opened about 2 months ago
by
spanielrassler
Can't loging to leaderboard to submit or vote. Too many redirects.
9
#853 opened 2 months ago
by
nisten
Were you hacked or is the crypto shit real?
2
#4 opened 3 months ago
by
pharaouk
this is garbage, phi-3-small model support doesnt exist yet
1
#1 opened 4 months ago
by
nisten
not getting coherent results from inferencing this in llama.cpp
#1 opened 5 months ago
by
nisten
This looks very good, just needs a math dpo run for the gsm8k score
1
#2 opened 5 months ago
by
nisten
broken
1
#1 opened 6 months ago
by
mradermacher
Update config.json
#1 opened 7 months ago
by
nisten
Is lm-eval-harness stuck again or just taking a while?
1
#611 opened 7 months ago
by
nisten
Add default chat template to tokenizer_config.json
1
#2 opened 7 months ago
by
Xenova
Create REBOOT.md
4
#586 opened 8 months ago
by
nisten
You try benchmarking yet?
1
#1 opened 8 months ago
by
devmandan
Improved quant
1
#2 opened 8 months ago
by
distantquant
Librarian Bot: Add merge tag to model
1
#1 opened 8 months ago
by
librarian-bot
Update config.json
1
#7 opened 9 months ago
by
zhaokai
Upload pytorch_model-00001-of-00002.bin
1
#4 opened 9 months ago
by
nisten
Upload pytorch_model-00002-of-00002.bin
#2 opened 9 months ago
by
nisten
model missing
7
#1 opened 9 months ago
by
barius
love the model but it's a duplicate on the 7b leaderboard
1
#1 opened 10 months ago
by
nisten
Optimizing 'airoboros-l2-?b-gpt4-2.0' for Limited Resources: Seeking Guidance
1
#2 opened about 1 year ago
by
Sidddd2020
HF upload bugged out again?
1
#2 opened about 1 year ago
by
nisten