No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from BananaMind/BananaMind-1.5-Base
All models by BananaMind →[Image blocked: banner]
BananaMind-1.5-Base is a small English causal language model trained from scratch by BananaMind.
It is our first fully pretrained medium model
[Image blocked: Benchmarks] A instruction tuned version is coming very soon.
Recommended starting settings:
For deterministic sanity tests:
BananaMind-1.5-Base was trained from scratch on approximately 27B tokens of FineWeb-Edu-style English web text.
The model uses a custom 32k byte-level BPE tokenizer and a compact Llama-style architecture with grouped-query attention.
BananaMind-1.5-Base uses a compact Llama-style decoder architecture:
Our model performs very good in comparison to other models:
[Image blocked: Benchmarks]
[Image blocked: Parameter vs size Chart]
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM
repo = "BananaMind/BananaMind-1.5-Base"
device = "cuda" if torch.cuda.is_available() else "cpu"dtype = torch.float16 if torch.cuda.is_available() else torch.float32
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=False)
model = AutoModelForCausalLM.from_pretrained( repo, trust_remote_code=False, dtype=dtype,).to(device)
model.eval()
prompt = "The color of the sky is blue. The color of a banana is"inputs = tok(prompt, return_tensors="pt").to(device)
with torch.no_grad(): out = model.generate( **inputs, max_new_tokens=16, do_sample=True, temperature=0.7, top_p=0.9, pad_token_id=tok.eos_token_id, eos_token_id=tok.eos_token_id, )
print(tok.decode(out[0], skip_special_tokens=True))temperature = 0.7top_p = 0.9max_new_tokens = 64do_sample = Falsemax_new_tokens = 8@misc{bananamind15base, title = {BananaMind-1.5-Base}, author = {BananaMind}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/BananaMind/BananaMind-1.5-Base}}}