GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
piyushgupta53
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
piyushgupta53
Model Tree
HuggingFaceTB/SmolLM2-135M-Instruct
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "piyushgupta53/smollm2-135m-english-to-latex-notation"system_prompt = ("Convert the user's English description of mathematical notation into LaTeX. ""Return exactly one standalone LaTeX expression. Do not include dollar signs, ""code fences, explanations, or any other text.")tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id,torch_dtype="auto",device_map="auto",)messages = [{"role": "system", "content": system_prompt},{"role": "user", "content": "Write the second derivative with respect to g of the fourth power of q evaluated at g."},]inputs = tokenizer.apply_chat_template(messages,add_generation_prompt=True,return_tensors="pt",).to(model.device)with torch.inference_mode():generated = model.generate(inputs,max_new_tokens=96,do_sample=False,pad_token_id=tokenizer.eos_token_id,)print(tokenizer.decode(generated[0, inputs.shape[-1]:], skip_special_tokens=True).strip())
Expected form:
text
\frac{d^2}{dg^2}q\left(g\right)^{4}
HuggingFaceTB/SmolLM2-135M-Instruct12fd25f77366fa6b3b4b768ec3050bf629380bacmerge_and_unload(safe_merge=True) into a clean float32 base with TF32 disabledThe adapter and merged model were compared with greedy decoding on all 400 frozen evaluation prompts. The local merged model and a fresh model loaded from this Hub repository produced exactly the same strings as the fresh adapter on every row.
Reproducibility note: the merge session intentionally used float32 with TF32 disabled and reproduced 387/400 exact strings from the earlier bfloat16 frozen evaluation run, despite byte-identical adapter/config/tokenizer artifacts and the same cached base revision. 13 outputs crossed greedy token boundaries across the precision/runtime change. This is recorded as numerical replay sensitivity around close logits, not model-file drift. The evaluation table below is the canonical frozen, fully adjudicated run; the merge-equivalence gate compares adapter and merged forms under the same current float32 runtime and batching.
| Evaluation | Rows | Normalized exact | Compiles | Complete semantic pass |
|---|---|---|---|---|
| Held-out benchmark | 200 | 44 (22.0%) | 197 (98.5%) | 131 (65.5%) |
| Distribution-gap diagnostic | 200 | 116 (58.0%) | 198 (99.0%) | 134 (67.0%) |
Diagnostic complete passes were 73/100 for wording shift and 61/100 for novel structures. Non-exact predictions were screened with DeepSeek V4 Flash and then every non-exact row was adjudicated with DeepSeek V4 Pro.
Compilation and semantic correctness are separate: valid LaTeX can still express the wrong meaning.
This is a narrow 135M-parameter model and is not reliable enough for unreviewed high-stakes use. It still fails many hard or unfamiliar structures. In the structural diagnostic it scored 0/10 on augmented matrices and 0/10 on indexed piecewise expressions with an otherwise branch.
Always validate both syntax and meaning when correctness matters. The model may also produce a correct expression that is textually different from a canonical reference.
Apache-2.0, consistent with the base model.