GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
RYVR
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
RYVR
Model Tree
Qwen/Qwen3-32B
Input Modalities
Output Modalities
Supported Functionality
This model is built for a consult architecture: an agent (or you) brings the live numbers — from Zoho Books, Tally, a spreadsheet — and the model brings the interpretation. Three trained behaviours follow from that:
1,926 instruction pairs — 26 hand-reviewed exemplars plus 1,900 synthetic advisory briefings from a deterministic scenario matrix (company profile × financial event × owner ask), generated with internally consistent financial snapshots and zero client-derived content. Every pair survived a five-gate gauntlet:
38 hand-written, never-in-training prompts; blind pairwise judging (4 independent judges, randomized A/B, identities hidden); both models generated on identical hardware.
| Test | Qwen3-32B base | This adapter |
|---|---|---|
| Scenario advisory quality (mean, 0–10) | 3.79 | 5.50 |
| Head-to-head win rate vs base (24 scenarios) | — | 75% (18W/6L) |
| Fabrication traps passed (metric not computable from given data) | 2/4 | 3/4 |
| Calibration probes passed (current-rate questions) | 5/10 | 8/10 |
| Brand/data leaks | 0 | 0 |
Recommended: run with thinking disabled (the adapter was trained in non-thinking mode) and this system prompt:
You are a seasoned fractional CFO advising Indian mid-market companies. Ground every derived figure in the client's actual numbers, hedge time-sensitive rates with 'confirm current', and give frameworks plus pull-lists when live data is required.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "Qwen/Qwen3-32B"adapter_id = "RYVR/qwen3-32b-cfo-brain-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)model = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(model, adapter_id) SYSTEM = ("You are a seasoned fractional CFO advising Indian mid-market companies. " "Ground every derived figure in the client's actual numbers, hedge time-sensitive " "rates with 'confirm current', and give frameworks plus pull-lists when live data is required.") question = """My Zoho cash flow confuses me: net profit ₹34L but cash went DOWN ₹28Lthe same month. Receivables up ₹41L, inventory up ₹19L, payables up ₹12L,loan EMI principal ₹14L. Explain what happened in plain language.""" messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": question}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=1500, temperature=0.4, top_p=0.9)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))bash
vllm serve Qwen/Qwen3-32B --enable-lora \ --lora-modules cfo-brain=RYVR/qwen3-32b-cfo-brain-lorafrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "Qwen/Qwen3-32B"adapter_id = "RYVR/qwen3-32b-cfo-brain-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)model = AutoModelForCausalLM.from_pretrained(base_id, torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(model, adapter_id) SYSTEM = ("You are a seasoned fractional CFO advising Indian mid-market companies. " "Ground every derived figure in the client's actual numbers, hedge time-sensitive " "rates with 'confirm current', and give frameworks plus pull-lists when live data is required.") question = """My Zoho cash flow confuses me: net profit ₹34L but cash went DOWN ₹28Lthe same month. Receivables up ₹41L, inventory up ₹19L, payables up ₹12L,loan EMI principal ₹14L. Explain what happened in plain language.""" messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": question}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)outputs = model.generate(inputs, max_new_tokens=1500, temperature=0.4, top_p=0.9)print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))vllm serve Qwen/Qwen3-32B --enable-lora \ --lora-modules cfo-brain=RYVR/qwen3-32b-cfo-brain-lora