janhq/vi-translation_v0.1_20250612-230103_Qwen3-1.7B_checkpoint-500_en-vi
Updated
•
30
Jan
company
Verified
AI & ML interests
Rethinking the Computer.
Recent Activity
View all activity
janhq's activity
thinhlpgÂ
published
a
model
about 15 hours ago
Post
1026
Don’t give up 🔥
Do you know what I was planning to do this time last week?
I was preparing to write a report declaring that Jan Nano was a failed project because the benchmark results didn’t meet expectations.
But I thought — it can’t be. When loading the model into the app, the performance clearly felt better. So why were the benchmark results worse?
That’s when I reviewed the entire benchmark codebase and realized something fundamental: agentic or workflow-based approaches introduce a huge gap and variation when benchmarking. Jan-nano was trained with an agentic setup — it simply can’t be benchmarked using a rigid workflow-based method.
I made the necessary changes, and the model ended up performing even better than before the issues arose. Turns out the previous benchmarking method conflicted with the way the model was trained.
What if I had given up? That would’ve meant 1.5 months of training and a huge amount of company resources wasted.
But now, this is officially the most successful and biggest release for the whole team — all thanks to Jan-nano.
Menlo/Jan-nano
Do you know what I was planning to do this time last week?
I was preparing to write a report declaring that Jan Nano was a failed project because the benchmark results didn’t meet expectations.
But I thought — it can’t be. When loading the model into the app, the performance clearly felt better. So why were the benchmark results worse?
That’s when I reviewed the entire benchmark codebase and realized something fundamental: agentic or workflow-based approaches introduce a huge gap and variation when benchmarking. Jan-nano was trained with an agentic setup — it simply can’t be benchmarked using a rigid workflow-based method.
I made the necessary changes, and the model ended up performing even better than before the issues arose. Turns out the previous benchmarking method conflicted with the way the model was trained.
What if I had given up? That would’ve meant 1.5 months of training and a huge amount of company resources wasted.
But now, this is officially the most successful and biggest release for the whole team — all thanks to Jan-nano.
Menlo/Jan-nano
jan-aiÂ
updated
a
model
9 days ago
jan-aiÂ
published
a
model
10 days ago
jan-aiÂ
published
a
model
11 days ago
jan-aiÂ
updated
a
model
11 days ago
jan-aiÂ
published
a
model
11 days ago
thinhlpgÂ
updated
a
dataset
25 days ago
thinhlpgÂ
published
a
model
28 days ago
thinhlpgÂ
updated
a
model
28 days ago
thinhlpgÂ
updated
a
model
about 1 month ago
thinhlpgÂ
published
a
model
about 1 month ago
thinhlpgÂ
published
a
dataset
about 1 month ago
thinhlpgÂ
updated
2
models
2 months ago
thinhlpgÂ
published
a
model
2 months ago
thinhlpgÂ
updated
a
model
2 months ago
thinhlpgÂ
published
2
models
2 months ago
thinhlpgÂ
updated
a
model
2 months ago