BananaMind/MiniBananaMind-v3-9M
Text Generation • 8.88M • Updated • 2
Banaxi Inc. PRO
Banaxi-Tech
AI & ML interests
SLMs, training from scratch, LoRA, TTS, Ternary models
Recent Activity
new activity about 3 hours ago
AxiomicLabs/Open_SLM_Leaderboard:Add https://huggingface.co/BananaMind/MiniBananaMind-v3-9M updated a model about 4 hours ago
BananaMind/MiniBananaMind-v3-9M published a model about 4 hours ago
BananaMind/MiniBananaMind-v3-9MOrganizations
Add https://huggingface.co/BananaMind/MiniBananaMind-v3-9M
1
#27 opened about 3 hours ago
by Banaxi-Tech
updated a
model about 4 hours ago
published a
model about 4 hours ago
replied to their post about 6 hours ago
Its Llama architecture
replied to their post about 6 hours ago
so the model you are training is "lamma For Casual LLM" or your custom architecture ?
Yes
replied to their post about 7 hours ago
Yeah definitely not, excited to see how it does when its fully trained!
Would be great to add winogrande to the leaderboard!
replied to their post about 7 hours ago
right now it would be #12 on the leaderboard <100M
replied to their post about 7 hours ago
ok then not terrible for mine 75M then
replied to their post about 7 hours ago
Yes, please
replied to their post about 7 hours ago
Benchmarks have gotten better at 210K
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| arc_challenge | 1 | none | 0 | acc | ↑ | 0.2073 | ± | 0.0118 |
| none | 0 | acc_norm | ↑ | 0.2398 | ± | 0.0125 | ||
| arc_easy | 1 | none | 0 | acc | ↑ | 0.4928 | ± | 0.0103 |
| none | 0 | acc_norm | ↑ | 0.4259 | ± | 0.0101 | ||
| hellaswag | 1 | none | 0 | acc | ↑ | 0.2892 | ± | 0.0045 |
| none | 0 | acc_norm | ↑ | 0.3077 | ± | 0.0046 | ||
| piqa | 1 | none | 0 | acc | ↑ | 0.6219 | ± | 0.0113 |
| none | 0 | acc_norm | ↑ | 0.6028 | ± | 0.0114 | ||
| winogrande | 1 | none | 0 | acc | ↑ | 0.4949 | ± | 0.0141 |
| === ArithMark-2.0 checkpoint-210000 === | ||||||||
| Average: 0.2588 (647/2500) |
replied to their post about 7 hours ago
With a MIN_LR of 3e-5 and LR=3e-4
Model idea
🔥 1
#2 opened about 7 hours ago
by Banaxi-Tech
updated a
model about 10 hours ago
🚩 Report: Illegal or restricted content
#1 opened about 13 hours ago
by Banaxi-Tech
posted an update about 13 hours ago
Post
72
Give us a follow at BananaMind. We are currently training two new models, so do not miss them when they release.
Here is what we are training:
BananaMind 1.5 Base
Our flagship 75M parameter model.
4096 token context window.
MiniBananaMind V3
Our 9M parameter model, targeting SOTA results for its size.
These will be released in the next few days.
BananaMind
Here is what we are training:
BananaMind 1.5 Base
Our flagship 75M parameter model.
4096 token context window.
MiniBananaMind V3
Our 9M parameter model, targeting SOTA results for its size.
These will be released in the next few days.
🚩 Report: Illegal or restricted content
#6 opened about 14 hours ago
by Banaxi-Tech
replied to their post about 16 hours ago
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | ||
|---|---|---|---|---|---|---|---|---|
| arc_challenge | 1 | none | 0 | acc | ↑ | 0.2073 | ± | 0.0118 |
| none | 0 | acc_norm | ↑ | 0.2381 | ± | 0.0124 | ||
| arc_easy | 1 | none | 0 | acc | ↑ | 0.4882 | ± | 0.0103 |
| none | 0 | acc_norm | ↑ | 0.4234 | ± | 0.0101 | ||
| hellaswag | 1 | none | 0 | acc | ↑ | 0.2880 | ± | 0.0045 |
| none | 0 | acc_norm | ↑ | 0.3038 | ± | 0.0046 | ||
| piqa | 1 | none | 0 | acc | ↑ | 0.6153 | ± | 0.0114 |
| none | 0 | acc_norm | ↑ | 0.5968 | ± | 0.0114 | ||
| winogrande | 1 | none | 0 | acc | ↑ | 0.5107 | ± | 0.0140 |
=== ArithMark-2.0 checkpoint-150000 ===
Average: 0.2540 (635/2500)
Random chance: 0.2500
By difficulty:
easy: 0.2528 (316/1250)
hard: 0.2320 (116/500)
medium: 0.2707 (203/750)
By operator_count:
1: 0.2528 (316/1250)
2: 0.2707 (203/750)
3: 0.2320 (116/500)
By topic:
addition: 0.1543 (83/538)
division: 0.5000 (65/130)
mixed_three_ops: 0.2479 (60/242)
mixed_two_ops: 0.2456 (97/395)
multiplication: 0.4375 (63/144)
parentheses_three_ops: 0.2171 (56/258)
parentheses_two_ops: 0.2986 (106/355)
subtraction: 0.2397 (105/438)
replied to their post about 16 hours ago
Im at 150K and the benchmarks arent that good, did this also happen to you with Supra 50M Base?
Just asking...
3
#1 opened 1 day ago
by 
LH-Tech-AI
Which measure?
1
#26 opened 1 day ago
by Banaxi-Tech