GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Sarath569
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
Sarath569
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Architecture | Llama (RoPE, SwiGLU, RMSNorm, tied embeddings) |
| Parameters | 125,848,320 |
| Layers / hidden / heads | 12 / 768 / 12 |
| Context length | 1024 |
| Vocab (byte-level BPE) | 16,384 |
| Precision | bf16 |
| Tokens seen | 4.08B (2 epochs over 2.04B) |
| Optimizer steps | 7,778 |
| Optimizer | AdamW (β=0.9/0.95, wd=0.1, grad-clip=1.0) |
| LR schedule | cosine 6e-4 → 6e-5, 200M-token warmup |
| Hardware | 8× H100 (data-parallel) |
| Final val loss / ppl | 2.3307 / 10.29 |
HFforLegal/case-law) — ~722M tokens (35%)PleIAs/SEC) — ~869M tokens (42%)HuggingFaceFW/fineweb-edu) — ~469M tokens (23%)Decontaminated against CaseHOLD / LexGLUE (case_hold) with 13-gram overlap filtering.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchtok = AutoTokenizer.from_pretrained("Sarath569/slm-125m-legal-base")model = AutoModelForCausalLM.from_pretrained("Sarath569/slm-125m-legal-base", torch_dtype=torch.bfloat16)ids = tok("The plaintiff shall bear the burden of", return_tensors="pt").input_idsout = model.generate(ids, max_new_tokens=60, do_sample=True, top_k=50, temperature=0.8)print(tok.decode(out[0], skip_special_tokens=True))
This is a small (~126M) base model, not instruction-tuned or aligned. It will produce
fluent but unreliable text, can hallucinate legal/financial facts, and must not be used
for legal or financial advice. Reserved chat tokens (<|user|>, <|assistant|>, <|system|>)
are present in the tokenizer for downstream fine-tuning.