BananaMind 2 Pico Test - 20%
This is the 20% checkpoint of a 900,002-parameter
base causal language model. It is not instruction tuned.
Architecture
| Field | Value |
|---|
| Parameters | 900,002 |
| Layers / hidden size | 6 / 96 |
| SwiGLU intermediate size | 380 |
| Query / KV heads | 6 / 2 |
| Head dimension | 16 |
| Context | 4,096 |
| Vocabulary | 384, tied |
| Refresh layers | 4 and 6 |
| Refresh kernel | Causal depthwise, width 9 |
The selective XSA refresh gate reads detached attention output as its signal,
reinjects the original input embedding as its value, and carries convolution
history alongside the K/V cache. Its learned residual scalar starts at zero.
Training
| Field | Value |
|---|
| Progress | 20% |
| Tokens seen | 40,001,077,248 |
| Target tokens | 200,000,000,000 |
| Hardware | 4 x NVIDIA H200 |
| Matrix optimizer | Stock torch.optim.Muon |
| Muon peak LR | 0.07 |
| Embedding/control optimizer | AdamW, LR 0.004 |
| Precision | bfloat16 autocast |
| Token range | FineWeb-HQ | Cosmopedia v2 |
|---|
| 0.00B-100.00B | 80% | 20% |
| 100.00B-200.00B | 60% | 40% |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "Banaxi-Tech/pico-test"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)