No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from BananaMind/BananaMind-2-Mini
All models by BananaMind →[Image blocked: Banner]
BananaMind-2-Mini is a small decoder-only causal language model trained from scratch by BananaMind on a 30B-token curriculum. It is our first model in the BananaMind 2 Series!
The model has 25,178,752 parameters, a 4,096 token context window, and a custom 8k-token digit-aware byte-level BPE tokenizer.
BananaMind-2-Mini uses a custom 8k byte-level BPE tokenizer trained from FineWeb-Edu text with digit-aware pre-tokenization.
Digits are kept as separate tokens so numbers do not collapse into large number tokens during tokenization.
Digit IDs:
Examples:
Special token IDs:
BananaMind-2-Mini was trained on a 30B-token mix of web, educational, synthetic textbook, and math data.
The run used a progressive curriculum rather than sampling the final aggregate mix from the first token.
Self-reported benchmark scores using lm_eval. Scores may vary a bit depending on harness version, runtime settings, dtype, and evaluation environment.
All task scores below use acc_norm,none. Average is the mean over ARC Easy, PIQA, ARC Challenge, and HellaSwag.
Higher is better on the y-axis, and more parameters are farther right on the x-axis. The top-left region represents the most score-efficient models.
[Image blocked: Parameters vs Average Score]
This model uses custom architecture code, so load it with trust_remote_code=True.
Install dependencies:
Run inference:
For stable continuations:
do_sample=Falserepetition_penalty=1.1max_new_tokens=64 to 160For more varied text:
do_sample=Truetemperature=0.6 to 0.8top_p=0.9top_k=50repetition_penalty=1.1max_new_tokens=64 to 192BananaMind-2-Mini is intended for lightweight language-model research, local experimentation, text continuation, tokenizer experiments, and small-model training comparisons.
Because this is a base model, prompts should be written as continuation prompts rather than chat messages.
Apache 2.0
🍌
18 -> [20, 27]227 -> [21, 21, 26]pip install -U transformers safetensors torchimport torchfrom transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "BananaMind/BananaMind-2-Mini"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
device = "cuda" if torch.cuda.is_available() else "cpu"dtype = ( torch.bfloat16 if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else torch.float32)
model = AutoModelForCausalLM.from_pretrained( model_id, trust_remote_code=True, torch_dtype=dtype,).to(device).eval()
prompt = "The color of the sky is"inputs = tokenizer(prompt, return_tensors="pt").to(device)
with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=96, do_sample=True, temperature=0.7, top_p=0.9, 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))