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
Sarath569/slm-125m-legal-base
Input Modalities
Output Modalities
Supported Functionality
The model uses the reserved chat tokens. Format each turn as:
markdown
<|user|>{your question}<|assistant|>{model answer}<|eos|>
databricks/databricks-dolly-15k — general instructions (~15k)gbharti/finance-alpaca — financial Q&A (~15k)dzunggg/legal-qa-v1 — US legal Q&A (~3.7k)Loss on assistant-response tokens only; LR 2e-5 cosine. Sensible decoding defaults
(repetition_penalty=1.3, no_repeat_ngram_size=3, temperature=0.7) are baked into
generation_config.json.
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("Sarath569/slm-125m-legal-chat")model = AutoModelForCausalLM.from_pretrained("Sarath569/slm-125m-legal-chat")prompt = "<|user|>\nExplain in simple terms what a 10-K filing is.\n<|assistant|>\n"ids = tok(prompt, add_special_tokens=False, return_tensors="pt").input_idsout = model.generate(ids, max_new_tokens=160) # decoding defaults come from generation_configprint(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
This is a ~125M model. After SFT it follows the chat format and produces fluent, legal/financial-flavored answers and stops appropriately, but it is not a reliable source of legal or financial facts — it hallucinates, and must not be used for legal, financial, or any real-world advice. It is best on general/common topics and weakest on precise domain facts. It is a base+SFT model with no alignment/RLHF. Intended for research and as a small fine-tuning starting point, not production use.