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-Medium-Chat
All models by BananaMind →[Image blocked: BananaMind 2 Medium Chat]
BananaMind-2-Medium-Chat is the instruction-tuned version of BananaMind-2-Medium. It was fully fine-tuned on HuggingFaceTB/smol-smoltalk using assistant-only loss masking.
The model has 49,559,552 parameters, a 3,072-token context window, and a custom 12,288-token digit-aware byte-level BPE tokenizer. It supports system prompts, multi-turn conversations, grouped-query attention, QK normalization, RoPE, tied embeddings, and KV-cached generation.
System and user messages were provided as context but masked from the loss. Only assistant content and the assistant-ending EOS token contributed to the training objective. All model parameters were trainable; no adapters or LoRA modules were used.
The tokenizer includes a Jinja chat template for system, user, and assistant messages. Its rendered structure is:
The role markers are plain text encoded with the existing tokenizer. No additional vocabulary entries were introduced during fine-tuning.
This model uses custom architecture code, so load it with trust_remote_code=True.
For multi-turn chat, append each generated assistant response to messages, add the next user message, and apply the chat template again.
For stable responses:
do_sample=Falserepetition_penalty=1.1max_new_tokens=128 to 256For more varied responses:
do_sample=Truetemperature=0.6 to 0.8top_p=0.9repetition_penalty=1.1max_new_tokens=128 to 256Always keep a finite generation limit. Small models can enter repetitive continuations on difficult or contradictory prompts.
Self-reported scores using lm_eval, the official ArithMark 2.0 script, and the internal BananaMind Instruction Bench. Scores may vary slightly by evaluation setup.
ARC Easy, ARC Challenge, PIQA, and HellaSwag use acc_norm,none.
BananaMind Instruction Bench (Internal)
* BananaMind Instruction Bench contains 100 examples: 40 General, 25 Multi-turn, 20 System Prompts, 10 Context Recall, and 5 Code. Supra 1.5 50M Instruct received conversation context through its ### Input field. Supra 1.0 50M Instruct used a copied checkpoint with 3.0x linear RoPE scaling, extending its context from 1,024 to 3,072 tokens without additional long-context training so it could fit the benchmark context.
[Image blocked: BananaMind 2 Medium Chat benchmarks]
This model is intended for small-model research, local chat experiments, instruction-tuning studies, educational demonstrations, and comparisons of compact language models.
Apache 2.0
<BOS><|system|>{system message}<|user|>{user message}<|assistant|>{assistant response}<EOS>pip install -U transformers safetensors torchimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "BananaMind/BananaMind-2-Medium-Chat"
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()
messages = [ { "role": "system", "content": "You are a concise and helpful assistant.", }, { "role": "user", "content": "Write a Python function that squares a number.", },]
inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", return_dict=True,)inputs = {name: tensor.to(device) for name, tensor in inputs.items()}
with torch.inference_mode(): output = model.generate( **inputs, max_new_tokens=256, do_sample=False, repetition_penalty=1.1, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id, use_cache=True, )
new_tokens = output[0, inputs["input_ids"].shape[1]:]print(tokenizer.decode(new_tokens, skip_special_tokens=True))Average = (HellaSwag + ((ARC Easy + ARC Challenge) / 2) + PIQA + ArithMark 2.0) / 4