GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Yoshita18
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
Yoshita18
Model Tree
mistralai/Mistral-7B-v0.1
Input Modalities
Output Modalities
Supported Functionality
This model is a LoRA/QLoRA fine-tuned version of Mistral-7B, specialized for answering questions related to health insurance.
It is designed to explain health insurance concepts in clear, plain English, similar to how a knowledgeable insurance representative or benefits counselor would explain them to a customer.
The model was fine-tuned on a synthetic instruction-following dataset containing health insurance questions and corresponding explanations.
The model is designed to answer questions such as:
Example:
Instruction
What is a deductible in health insurance?
Response
A deductible is the amount you must pay out-of-pocket for covered healthcare services before your insurance company begins paying for eligible medical expenses. Once the deductible has been met, you generally share costs with the insurer according to your plan's copayment or coinsurance rules.
The model is intended for:
This model is not intended to:
The model explains concepts in a general educational context and should not be considered legal, medical, or insurance advice.
The model was fine-tuned using a synthetic instruction-following dataset covering health insurance topics.
Each example follows the format:
markdown
### Instruction:<Question>### Response:<Explanation>
Topics include:
| Parameter | Value |
|---|---|
| Epochs | 3 |
| Batch size | 4 |
| Gradient Accumulation | 4 |
| Learning Rate | 2e-4 |
| Max Sequence Length | 512 |
| Optimizer | AdamW |
| Scheduler | Cosine |
| Quantization | 4-bit NF4 |
The model was evaluated using:
| Metric | Score |
|---|---|
| ROUGE-1 | 0.5317 |
| ROUGE-2 | 0.2286 |
| ROUGE-L | 0.3614 |
| Metric | Score |
|---|---|
| Precision | 0.9153 |
| Recall | 0.9041 |
| F1 | 0.9096 |
python
from transformers import AutoTokenizerfrom peft import AutoPeftModelForCausalLMmodel_id = "Yoshita18/mistral-finetuned"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoPeftModelForCausalLM.from_pretrained(model_id,device_map="auto")prompt = """### Instruction:Explain what coinsurance is.### Response:"""inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs,max_new_tokens=150)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:],skip_special_tokens=True,))
This model has several limitations:
This model is suitable for:
This model is released under the Apache 2.0 License.
The base model is:
Please ensure compliance with the base model license when using this adapter.
If you use this model in your work, please cite this repository.
markdown
@misc{yoshita18_health_insurance_mistral,title={Mistral Fine-Tuned for Health Insurance Question Answering},author={Yoshita},year={2026},publisher={Hugging Face},howpublished={\url{https://huggingface.co/Yoshita18/mistral-finetuned}}}