GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
timothywong731
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
timothywong731
Model Tree
timothywong731/tim-360m-base
Input Modalities
Output Modalities
Supported Functionality
ChatML. Turns are wrapped <|im_start|>{role}\n{content}<|im_end|>; the assistant turn ends on <|im_end|> (token id 2), which is the model's generation stop token. Use the tokenizer's chat template — don't hand-format.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("timothywong731/tim-360m-instruct")m = AutoModelForCausalLM.from_pretrained("timothywong731/tim-360m-instruct", torch_dtype=torch.bfloat16)msgs = [{"role": "user", "content": "Explain what a transformer is in two sentences."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt")out = m.generate(ids, max_new_tokens=200, do_sample=True, temperature=0.7, top_p=0.9)print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=True))
Identical to the base model: SmolLM2-360M skeleton, pre-LN RMSNorm, RoPE (θ=100000), SwiGLU, grouped-query attention (15 query / 5 KV heads) with per-head QK-norm, tied embeddings, no biases. 32 layers, hidden 960, head_dim 64, FFN 2560, vocab 49,152. Context: max_position_embeddings 4096, trained at seq_len 2048.
lm-evaluation-harness (0.4.12), 0-shot, acc_norm where applicable:
| HellaSwag | ARC-Easy | ARC-Challenge | PIQA | WinoGrande | OpenBookQA | SciQ | SocialIQA | CommonsenseQA | WikiText (bpb ↓) |
|---|---|---|---|---|---|---|---|---|---|
| 0.395 | 0.501 | 0.262 | 0.652 | 0.524 | 0.302 | 0.714 | 0.408 | 0.203 | 1.130 |
Post-training preserved base capability — most tasks move within noise of the base model, with a real gain on SocialIQA (+3.0) and small gains on HellaSwag / OpenBookQA. WikiText bits-per-byte rises (1.06 → 1.13), as expected: a chat-tuned model is no longer a pure next-token predictor of raw web text.
Small (360M) and lightly trained (~30B pretraining tokens, then light post-training). Instruction-following is basic — expect short, sometimes shallow answers, weak arithmetic and multi-step reasoning, and confident hallucination. English-only. DPO is not safety alignment — this model has no dedicated safety tuning; filter before exposing to end users.
Apache-2.0. Pretraining data (all named, public): FineWeb-Edu (ODC-BY), DCLM-Baseline (CC-BY-4.0), Stack-Edu, FineMath (ODC-BY). Post-training data: smol-smoltalk and ultrafeedback_binarized (see their dataset cards for licenses). No gated or scraped-private data.