GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Sudhanshu1985
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
Sudhanshu1985
Model Tree
thesreedath/slm-125m-base
Input Modalities
Output Modalities
Supported Functionality
| Base | After QA SFT | |
|---|---|---|
| Loss | 2.61 | 0.69 |
| Perplexity | 13.61 | 2.00 |
Trained on one exact format, shipped in tokenizer_config.json:
markdown
<|bos|><|system|>SYSTEM<|user|>USER<|assistant|>ANSWER<|eos|>
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("Sudhanshu1985/slm-125m-sft")model = AutoModelForCausalLM.from_pretrained("Sudhanshu1985/slm-125m-sft")msgs = [{"role": "system", "content": "You are a legal and financial assistant. Answer only from the provided context. If the answer is not in the context, say so."},{"role": "user", "content": "Context:\n<your passage>\n\nWhat date was suit filed?"},]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)enc = tok(text, return_tensors="pt", add_special_tokens=False)enc = {k: v for k, v in enc.items() if k in ("input_ids", "attention_mask")}print(tok.decode(model.generate(**enc, max_new_tokens=90)[0][enc["input_ids"].shape[1]:],skip_special_tokens=True))
24,713 grounded-QA pairs (23,204 train / 474 val after filtering to the 1024-token window), synthesized from a cleaned legal/financial + web corpus and filtered by an LLM judge (1-5 rubric for correctness + grounding; kept >= 4):
| Source | Pairs | Share |
|---|---|---|
US case law (HFforLegal/case-law) | 13,005 | 52.6% |
SEC filings (PleIAs/SEC) | 9,309 | 37.7% |
Educational web (HuggingFaceFW/fineweb-edu) | 2,399 | 9.7% |
Task types: lookup, reasoning, and unanswerable (refusals). ~32% of the pairs are unanswerable, which directly trains reliable refusal behavior.
Recipe: 3 epochs, 1xH100, lr 2e-5 cosine, AdamW, bf16, effective batch 32, loss on the assistant span only.
| Prompt type | Example output |
|---|---|
| lookup | "The plaintiff filed suit on March 14, 1994..." |
| reasoning | "...because DeWitt failed to establish that Northstar had actual or constructive notice of the defect." |
| unanswerable | "That is not stated in the context." |