GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MLVXN
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
MLVXN
Model Tree
HuggingFaceTB/SmolLM2-135M
Input Modalities
Output Modalities
Supported Functionality
Trained on TPU with max length 1024, per device batch 32, AdaFactor, cosine schedule, warmup 500 steps, weight decay 0.01.
Final loss 1.337 after 33732 steps.
python
from transformers import AutoTokenizer, AutoModelForCausalLMtok = AutoTokenizer.from_pretrained("MLVXN/Adurite1-135M-COT")model = AutoModelForCausalLM.from_pretrained("MLVXN/Adurite1-135M-COT")prompt = "<|im_start|>user\nWhat is 12*8? Think step by step.<|im_end|>\n<|im_start|>assistant to=self thinking\n"inputs = tok(prompt, return_tensors="pt")out = model.generate(**inputs, max_new_tokens=200, do_sample=False)print(tok.decode(out[0], skip_special_tokens=True))
Or use the GGUF file with llama.cpp:
bash
llama-cli -m adurite1-135m-cot-f16.gguf -p "What is 12*8? Think step by step."
GGUF weights are available in this repo:
adurite1-135m-cot-f16.gguf 313 MB full precisionadurite1-135m-cot-q4_k_m.gguf quantized 4 bit (when available)Work in progress. Early MMLU and GSM8K runs are being added. MMLU is expected around 33 to 36 percent, GSM8K around 45 to 50 percent with chain of thought prompting.
This is a 135M model. It can do short reasoning traces of 2 to 4 steps but will fail on hard math and long logic problems. It may repeat or miss facts. Use with care and check outputs for important tasks.
Apache 2.0
markdown
@misc{adurite1-135m-cot,title = {Adurite1-135M-COT},author = {MLVXN},year = {2026},url = {https://huggingface.co/MLVXN/Adurite1-135M-COT}}