🔄 In a Training Loop
Mithula Artigala
QyrouNnet-AI
AI & ML interests
None yet
Recent Activity
liked a dataset 6 days ago
r0b0tlab/qwen3.8-max-glm5.2-kimi-k3-distillation updated a model 6 days ago
Qyrou/Vega-1-65m-exp-base liked a model 12 days ago
AxiomicLabs/GPT-X2.5-135MOrganizations
Question
🔥 1
27
#1 opened 16 days ago
by
Banaxi-Tech
training data
3
#2 opened 14 days ago
by
QyrouNnet-AI
yo im training a 35m model on 2b tokens of 4 fineweb edu 2024 snapshots
5
#5 opened 16 days ago
by
RexTRO111
FineTune in this
14
#2 opened 15 days ago
by
MishaGGG
20M model?
🤗 1
2
#4 opened 19 days ago
by
QyrouNnet-AI
added button try supra
#5 opened 19 days ago
by
QyrouNnet-AI
Bots uploading in DALL-E mini Community. Hope this doesn't happen to SupraLabs.
😔 4
1
#6 opened 20 days ago
by
RexTRO111
small model --> big context --> human monkey brain --> happy!
2
#1 opened 20 days ago
by
QyrouNnet-AI
training data
#1 opened 20 days ago
by
QyrouNnet-AI
broken space
#1 opened 20 days ago
by
QyrouNnet-AI
No new models? :(
4
#5 opened 22 days ago
by
RexTRO111
Benchmark Score Accuracy
😎 1
#1 opened 20 days ago
by
QyrouNnet-AI
Why not just use <think></think>?
👍 1
4
#3 opened 2 months ago
by
FlameF0X
purpose of the dataset is unclear for me
2
#3 opened about 1 month ago
by
QyrouNnet-AI
Appreciation, and a question
3
#1 opened 23 days ago
by
QyrouNnet-AI
Where is the deduped dataset?
2
#3 opened 24 days ago
by
QyrouNnet-AI
Multi Turn Dataset
#2 opened 24 days ago
by
QyrouNnet-AI
DPO is required
🤗 1
4
#1 opened 26 days ago
by
QyrouNnet-AI
Question about rejection sampling and reliability of assistant responses
🔥 1
1
#3 opened 27 days ago
by
Bklight999