GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Bluebox85033
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Bluebox85033
Model Tree
Qwen/Qwen2.5-3B
Input Modalities
Output Modalities
Supported Functionality
pass@1, greedy decoding. Base is the unmodified Qwen2.5-3B evaluated under the same prompts and decoding.
| Benchmark | Base | Cogito-3B | n |
|---|---|---|---|
| Countdown (solve rate) | 7.8% | 64.1% | 64 |
| GSM8K | 81.0% | 82.3% | 300 |
| MATH-500 | 55.0% | 64.3% | 300 |
The largest change is on Countdown, a task under-represented in standard pretraining, where the base model rarely emits a valid solution. GSM8K sits near this base model's ceiling under the given prompt, so the change there is small. Sampled reasoning traces are provided in results/aha_transcripts.md.
Qwen/Qwen2.5-3BAssistant: <think>\n and the model completes … </think> <answer> … </answer>Cogito-3B is a base completion model, not an instruction/chat model. It expects the training prompt format shown below.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Bluebox85033/cogito-3b"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") def countdown_prompt(nums, target): return ( "A conversation between User and Assistant. The User poses a Countdown number puzzle, and the Assistant solves it.\n" "The Assistant first reasons step by step inside <think> </think> tags, and then gives ONLY the final arithmetic expression inside <answer> </answer> tags.\n" "Rules: use each given number exactly once; the only allowed operations are + - * / and parentheses; the expression must evaluate exactly to the target.\n" "Example answer format: <answer>(3 + 5) * 2</answer>\n\n" f"User: Numbers: {nums}. Target: {target}. Find an expression that uses each number exactly once and equals {target}.\n" "Assistant: <think>\n" ) prompt = countdown_prompt([3, 5, 2], 16)inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=1024, do_sample=False) # greedyprint("<think>\n" + tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))For math, use the same structure with the math template (final answer as \boxed{...}):
python
def math_prompt(problem): return ( "A conversation between User and Assistant. The User asks a math question, and the Assistant solves it.\n" "The Assistant first reasons step by step inside <think> </think> tags, and then gives the final answer inside <answer> </answer> tags, written as \\boxed{...}.\n" "Example answer format: <answer>\\boxed{42}</answer>\n\n" f"User: {problem}\n" "Assistant: <think>\n" )Two-stage curriculum:
(sorted numbers, target). Reward: the model's expression must use each number exactly once with only + - * / ( ), and evaluate exactly to the target.\boxed{} answer equivalence to ground truth.Across steps, mean reward increases and mean completion length grows. Full data generation, reward functions, and training/evaluation code are in the GitHub repository and under recipe/ in this repo.
pass@1 with greedy decoding on held-out splits. The Countdown test set is self-generated and disjoint from training; GSM8K uses the official test split; MATH-500 is HuggingFaceH4/MATH-500. Sample sizes are given in the results table; the Countdown set (n=64) is small and its figure should be read as indicative.
The method (RLVR / GRPO) and the Countdown demonstration follow DeepSeek-R1-Zero and the TinyZero reproduction. This model is a reproduction and extension rather than a new method: it provides an end-to-end reproducible pipeline and a Countdown→math curriculum with a controlled before/after measurement on held-out splits.
bibtex
@misc{cogito3b, title = {Cogito-3B: GRPO reasoning training on Qwen2.5-3B (Countdown and math)}, author = {Bluebox85033}, year = {2026}, howpublished = {\url{https://huggingface.co/Bluebox85033/cogito-3b}}}import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Bluebox85033/cogito-3b"tok = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") def countdown_prompt(nums, target): return ( "A conversation between User and Assistant. The User poses a Countdown number puzzle, and the Assistant solves it.\n" "The Assistant first reasons step by step inside <think> </think> tags, and then gives ONLY the final arithmetic expression inside <answer> </answer> tags.\n" "Rules: use each given number exactly once; the only allowed operations are + - * / and parentheses; the expression must evaluate exactly to the target.\n" "Example answer format: <answer>(3 + 5) * 2</answer>\n\n" f"User: Numbers: {nums}. Target: {target}. Find an expression that uses each number exactly once and equals {target}.\n" "Assistant: <think>\n" ) prompt = countdown_prompt([3, 5, 2], 16)inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=1024, do_sample=False) # greedyprint("<think>\n" + tok.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))def math_prompt(problem): return ( "A conversation between User and Assistant. The User asks a math question, and the Assistant solves it.\n" "The Assistant first reasons step by step inside <think> </think> tags, and then gives the final answer inside <answer> </answer> tags, written as \\boxed{...}.\n" "Example answer format: <answer>\\boxed{42}</answer>\n\n" f"User: {problem}\n" "Assistant: <think>\n" )@misc{cogito3b, title = {Cogito-3B: GRPO reasoning training on Qwen2.5-3B (Countdown and math)}, author = {Bluebox85033}, year = {2026}, howpublished = {\url{https://huggingface.co/Bluebox85033/cogito-3b}}}