GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
nitin1pawar
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
nitin1pawar
Model Tree
nitin1pawar/slm125m-base
Input Modalities
Output Modalities
Supported Functionality
markdown
<|bos|><|system|>{system}<|user|>{user}<|assistant|>{answer}<|eos|>
tokenizer.apply_chat_template is configured, so:
python
messages = [{"role": "system", "content": "You are a legal and financial assistant. ..."},{"role": "user", "content": "Passage 1:\n...\n\nQuestion: ..."},]prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
When the passages do not contain the answer the model replies:
The passage does not provide enough information to answer this question.
10,000 synthetic Q&A pairs generated with gpt-5-mini from the model's own
pretraining corpus (US case law + SEC filings + educational web text), then graded by an
LLM judge on groundedness, correctness, answerability and form. Judge pass rate
88.4%. Questions were deduplicated by exact hash and by 5-gram
Jaccard overlap.
Passages were drawn from the deduplicated and decontaminated corpus, so CaseHOLD and
LexGLUE case_hold remain genuinely held out.
| slice | share |
|---|---|
| closed_book | 1,584 |
| instruction | 787 |
| negative | 2,511 |
| positive | 5,118 |
148 steps over 1 epochs (9.7M tokens, 62s on 1×H100), full-parameter (no LoRA), AdamW, peak LR 8e-05 cosine to 0, bf16. Loss is computed on answer tokens only — question and context tokens are masked out.
| metric | value |
|---|---|
| Val answer-token loss | 1.6840 (ppl 5.39) |
| Refusal recall (no answer in context → refuses) | 91.0% |
| False refusal rate (answer present → wrongly refuses) | 15.3% |
| Base-corpus perplexity after SFT | 10.56 (was 8.11 before) |
125M parameters. It produces fluent but frequently incorrect legal and financial text, its knowledge is bounded by a 2.07B-token corpus, and the training answers were written by another language model rather than by lawyers. Context is capped at 1,024 tokens. Not legal or financial advice.