GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AbhijithSK
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
AbhijithSK
Model Tree
mistralai/Mistral-7B-Instruct-v0.2
Input Modalities
Output Modalities
Supported Functionality
| Metric | Value |
|---|---|
| Final Train Loss | 0.022 |
| Token Accuracy | 98.9% |
| Epochs | 3 |
| Training Time | ~2h 50min on T4 GPU |
| Trainable Params | 13.6M / 7.25B (0.19%) |
from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model = PeftModel.from_pretrained(base, "AbhijithSK/mistral-7b-medical-instruct") tokenizer = AutoTokenizer.from_pretrained("AbhijithSK/mistral-7b-medical-instruct")
For research only. Not for clinical use. Always consult a qualified physician.
Abhijith SK - GitHub: https://github.com/AbhijithSK