DynamicMind-Mini
DynamicMind-Mini is a decoder-only model trained on FineWeb-Edu, SmolLM-Corpus and FineMath
The model has about 8.9M parameters and its based on MiniBananaMind-v4-9M architecture with a custom 8k-token byte-level BPE tokenizer with digit-aware tokenization.
Model Details
| Field | Value |
|---|---|
| Parameters | 8,884,992 |
| Architecture | Custom Llama-style decoder |
| Layers | 9 |
| Hidden size | 256 |
| Intermediate size | 768 |
| Attention heads | 8 |
| KV heads | 2 |
| Vocabulary size | 8,192 |
| Context length | 1,024 |
| Embeddings | Tied input/output embeddings |
| Weight format | safetensors |
Tokenizer
DynamicMind-Mini uses the same digit-aware 8k tokenizer as MiniBananaMind-v4-9M.
Digits are kept as separate tokens so numbers do not collapse into large number tokens during tokenization.
Digit IDs:
| Token | ID |
|---|---|
1 |
9 |
2 |
10 |
3 |
11 |
4 |
12 |
5 |
13 |
6 |
14 |
7 |
15 |
8 |
16 |
9 |
17 |
0 |
18 |
Usage
This model uses custom architecture code, so load it with trust_remote_code=True.
Install dependencies:
pip install -U transformers safetensors torch
Run inference:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "DedeProGames/DynamicMind-Mini"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id,
trust_remote_code=True,
torch_dtype=torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else torch.float16,
).cuda().eval()
prompt = "The meaning of life is "
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
with torch.no_grad():
output = model.generate(
input_ids=input_ids,
max_new_tokens=64,
do_sample=False,
repetition_penalty=1.1,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0], skip_special_tokens=True))