A1 is a reasoning-tuned version of schneewolflabs/A0i-12B (Mistral Nemo–class, 12B). It was supervised-fine-tuned on schneewolflabs/BigDenker-SFT to produce explicit <think>…</think> chain-of-thought before its final answer.

What's different from the base model

The base A0i-12B does not reason — given a prompt it answers directly. A1 produces a reasoning trace inside <think></think> and then the answer, in the Qwen3 thinking convention.

The reasoning tokens were added without resizing the vocabulary. A0i's tokenizer ships with 986 unused reserved slots (<SPECIAL_14>…<SPECIAL_999>); ten of these were repurposed in place (token IDs unchanged, so embeddings were not resized):

ID	token	ID	token
14	`<think>`	19	`</tool_response>`
15	`</think>`	20	`<\|vision_start\|>`
16	`<tool_call>`	21	`<\|vision_end\|>`
17	`</tool_call>`	22	`<\|image_pad\|>`
18	`<tool_response>`	23	`<\|video_pad\|>`

Before training, these rows (which were zero/untrained in the base) were initialized from the mean of their surface string's sub-token embeddings (computed separately for embed_tokens and lm_head, which are untied), with a small symmetry-breaking perturbation. They were then trained as part of the finetune.

Note: the vision/tool tokens exist for chat-template completeness. A1 is a text-only model and was not trained on vision or tool-calling data.

Usage

A1 uses a Qwen3-style chat template (bundled as chat_template.jinja). The template injects <think>\n as the assistant prefix, so the model continues with its reasoning, emits </think>, then the answer. Always use the chat template — using the model without it will not trigger reasoning.

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("schneewolflabs/A1")
model = AutoModelForCausalLM.from_pretrained(
    "schneewolflabs/A1", dtype=torch.bfloat16, device_map="auto"
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "A bat and ball cost $1.10. The bat is $1.00 more than the ball. How much is the ball?"},
]
enc = tok.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
).to(model.device)
out = model.generate(**enc, max_new_tokens=1024, do_sample=False)
print(tok.decode(out[0][enc["input_ids"].shape[1]:], skip_special_tokens=False))

The output has the form …reasoning…</think>\n\n…final answer…<|im_end|>.

Training

Method: SFT, 1 epoch, via the Merlina training system (grimoire SFTLoss, prompt-masked completion).
Adaptation: LoRA (r=64, α=128, dropout 0.05) on attention + MLP projections, plus embed_tokens and lm_head as fully-trained modules_to_save (required so the repurposed token rows actually learn).
Hyperparameters: lr 2e-5 (cosine, 5% warmup), effective batch 16 (bs 1 × grad-accum 16), max sequence length 4096, bf16, seed 42.
Split: 90% train / 10% held-out eval (random, seed 42).
Result: train loss 1.22 → 0.687; held-out eval loss ≈ 0.653 (eval ≤ train — no overfitting at 1 epoch).
The conservative learning rate plus the semantic embedding initialization were chosen to add reasoning while limiting drift of the base model's general token representations (the full embedding/lm_head matrices were trainable).

Evaluation notes

Behavioral checks show coherent step-by-step reasoning that generalizes beyond the training distribution — e.g. it solves the bat-and-ball problem correctly ($0.05) and explicitly rejects the common intuitive-trap answer.

Limitations

Always-on thinking: the template starts every assistant turn with <think>; the model reasons even on trivial prompts. A non-thinking path exists via the template (enable_thinking=False injects an empty <think></think>) but was not specifically tuned.
Single-source SFT: trained on one dataset/style (BigDenker), so reasoning phrasing is fairly homogeneous.
One epoch / conservative LR: a deliberate, safe first pass — not exhaustively tuned.
Inherits all limitations and biases of the base model and the SFT data.

Provenance

Base: schneewolflabs/A0i-12B · Data: schneewolflabs/BigDenker-SFT · Tokenizer/template: repurposed reserved tokens + Qwen3 chat template.