GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
jonam-ai
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
jonam-ai
Model Tree
thesreedath/slm-125m-base
Input Modalities
Output Modalities
Supported Functionality
The base model, given "In a breach of contract claim, the plaintiff…", would ramble onward. This model, asked a question, answers it:
Q: In a breach of contract claim, what must the plaintiff prove? A: The plaintiff must show: (1) a contract; (2) an agreement to perform a specific act; (3) an obligation to perform…
The tokenizer has role special tokens but no chat template, so format prompts
manually as <|bos|><|system|>{system}<|user|>{question}<|assistant|> and let the
model complete the answer up to <|eos|>:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("jonam-ai/legal-slm-125m-sft")model = AutoModelForCausalLM.from_pretrained("jonam-ai/legal-slm-125m-sft", torch_dtype=torch.bfloat16)system = "You are a knowledgeable legal and financial assistant. Answer accurately and concisely."question = "What is the purpose of a Form 10-K filing?"def sid(t): return tok.convert_tokens_to_ids(t)ids = (tok("<|bos|>", add_special_tokens=False)["input_ids"]+ [sid("<|system|>")] + tok(system, add_special_tokens=False)["input_ids"]+ [sid("<|user|>")] + tok(question, add_special_tokens=False)["input_ids"]+ [sid("<|assistant|>")])out = model.generate(torch.tensor([ids]), max_new_tokens=120, do_sample=True,temperature=0.7, top_p=0.9, eos_token_id=sid("<|eos|>"),pad_token_id=sid("<|pad|>"))print(tok.decode(out[0][len(ids):], skip_special_tokens=True))
5,846 grounded question–answer pairs, synthesized with a teacher-LLM distillation pipeline over a cleaned corpus of US case law, SEC filings, and educational web text:
Mix: case-law 45% · SEC 45% · web 10%. Split: 5,554 train / 292 val.
| Method | full fine-tune (not LoRA) |
| Hardware | 1 × NVIDIA L4 |
| Epochs | 2 |
| Tokens seen | ~1.0M |
| LR | 3e-5, cosine decay, 3% warmup |
| Precision | bf16 compute, fp32 master weights |
| Time | ~80 seconds |
125M parameters, English only, 1,024-token context, not aligned/RLHF'd. It imitates the form of grounded answers learned from a synthetic dataset; factual reliability is limited by model size. Not legal or financial advice.