Loading…
Loading…
English experimental dense Llama model trained from random weights; 29,699,712 unique parameters. Full Safetensors weights and tokenizer are included. Developed by Convergent.
Identity checks: 2/2. Unrelated answers show repetition and factual errors. General usefulness is limited and no coding benchmark was passed or claimed.
from transformers import AutoTokenizer, AutoModelForCausalLM
repo = "Convergent-ch/Alpina-Small-2.0-30M"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)
messages = [{"role": "system", "content": "You are a helpful English-speaking assistant. Be clear, accurate, and concise."}, {"role": "user", "content": "Who are you?"}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True)
output = model.generate(**inputs, max_new_tokens=80, do_sample=False)
print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Research release with very limited evaluation. Identity claims describe the customization and do not change the original model authorship. See evaluation.json for actual generated answers. Do not infer benchmark quality from successful name responses.
Training sources include prefixes of SmolLM-Corpus (ODC-BY), permissively filtered CodeParrot, Smol-SmolTalk (Apache-2.0), and self-oss-instruct-sc2-exec-filter-50k (ODC-BY). See provenance files where supplied. Original dataset notices and licenses apply to the source data; the training datasets are not redistributed here. No affiliation with Qwen or dataset authors is implied.
ollama run girgineron/alpina-small-2.0:30m
The F16 GGUF is also included here. The Modelfile uses the trained chat format with LF newlines. No retraining was performed during conversion.