Teknium
teknium
AI & ML interests
None yet
Organizations
teknium's activity
Nice :) Can you share the mergekit config?
#1 opened 8 days ago
by
Weyaxi
Model License
#5 opened 3 days ago
by
inkasaras
Dataset Sources Missing
1
#14 opened 1 day ago
by
cinjonr
GPU gets overloaded after certain conversation
1
#3 opened 7 days ago
by
GokhanAI
Can you guys make a merge that writes naturally as a human being?
1
#2 opened 8 days ago
by
AIGUYCONTENT
Is this already or will there be a version thats been abliterated/orthogonalized?
1
#4 opened 7 days ago
by
belisarius
Can you share the script that generated this
1
#3 opened 8 days ago
by
teknium
Prompt Template
2
#4 opened 23 days ago
by
venkatpr
Not surrounding function_call with <tool_call> tags.
3
#5 opened 21 days ago
by
markov-aug
Generation of response not stopping, keeps "talking" with itself.
2
#8 opened 15 days ago
by
daniq
Reasoning?
1
#6 opened 21 days ago
by
urtuuuu
Updated Path
1
#7 opened 21 days ago
by
zxxatxxz
add axolotl tag
#1 opened 22 days ago
by
winglian
Is there a plan to use llama3 ?
2
#11 opened 22 days ago
by
supercharge19
License
1
#13 opened about 1 month ago
by
oscarwang2
Adding `safetensors` variant of this model
#14 opened about 2 months ago
by
SFconvertbot
nous-hermes-llama2
1
#16 opened 30 days ago
by
Machforr
Update README.md
#8 opened 4 months ago
by
tomwalsz
Update README.md
2
#12 opened about 1 month ago
by
Nekochu
Datasets for function calling and JSON
5
#13 opened about 2 months ago
by
Andriy
Can you upload also the tokenizer.json?
4
#11 opened 2 months ago
by
nmaroulis
Vocabulary Size?
2
#10 opened 2 months ago
by
MH1P
Very good job especially on enhanced ability of structured output!
3
#9 opened 2 months ago
by
daisr
Can you provide a data template for fine-tuning the model?
1
#7 opened 2 months ago
by
wadesss
bigger Hermes 2 Pro God
2
#6 opened 2 months ago
by
prudant
Add Padding Tokens
1
#12 opened about 2 months ago
by
zxybazh
Amazon Sagemaker deployment
3
#11 opened 2 months ago
by
jdmiwx
Custom Quantization Types
7
#2 opened 2 months ago
by
christopherthompson81
License?
2
#9 opened 3 months ago
by
lewtun
Add license
#10 opened 2 months ago
by
saattrupdan
Add license
#3 opened 2 months ago
by
saattrupdan
Port it to ollama
3
#1 opened 2 months ago
by
Alivevi
Fix minor Typo README
2
#1 opened 2 months ago
by
chrislevy
is this filtered(cencored) or not? can i run it on 3090?
3
#1 opened 2 months ago
by
Avos0001
Bug: fix the rope_scaling
3
#2 opened 9 months ago
by
alfredplpl
Thanks
1
#2 opened 3 months ago
by
amgadhasan
How did you train this without going OOM in RAM & VRAM?
3
#15 opened 3 months ago
by
vicplus
No responses
4
#9 opened 3 months ago
by
emilios
Request: DOI
1
#7 opened 3 months ago
by
paulgavrikov
Update examples in README to be compatible with ChatWidget
#6 opened 3 months ago
by
Wauplin
Update examples in README to be compatible with soon-to-come ChatWidget
#8 opened 3 months ago
by
Wauplin
Update README.md
#1 opened 3 months ago
by
NickyNicky
[bot] Conversion to Parquet
#1 opened 6 months ago
by
parquet-converter
Empty columns
2
#4 opened 4 months ago
by
PhilipMay
performance issue with hf 4bit
3
#8 opened 4 months ago
by
FinancialSupport
Does head-to-head loss on the evaluation set measure capabilities or merely style?
1
#1 opened 4 months ago
by
lewtun
Update to use `synthetic` tag
#5 opened 4 months ago
by
davanstrien
Update README.md
#7 opened 4 months ago
by
arpitingle
Will it be public?
5
#2 opened 6 months ago
by
Ricepig
Update to use `synthetic` tag
1
#6 opened 4 months ago
by
davanstrien
Add miku.mp4 to the readme
6
#7 opened 4 months ago
by
modster
How much VRAM does this model need?
6
#21 opened 4 months ago
by
Ziizu
ChatML without SystemPrompt doesn't work well
4
#2 opened 4 months ago
by
andreP
Training code?
4
#5 opened 7 months ago
by
umarmnaq
Is the SFT phase a full finetune or a lora?
3
#3 opened 4 months ago
by
dividebythree
License
1
#7 opened 4 months ago
by
AndrewmMAQ
Endless response
2
#1 opened 4 months ago
by
alexfilus