Downloads · 30 days
24
18% of all-time downloads
yogvidwankhede/healthmate-mistral-7b-medical-lora
healthmate-mistral-7b-medical-lora is a text generation model from yogvidwankhede. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
Notice (2026-10-01): these adapters are unusable. We checked every tensor in all three adapter files (root = seed 42, adapterseed123, adapterseed999): all 448 tensors in each file contain NaN, so any model loaded with…
Downloads · 30 days
24
18% of all-time downloads
All-time downloads
132
Public
Repo size
84 MB
Likes
0
Public
Click a slice to open those files.
.safetensors252 MB · 96%
From the Hugging Face model README
Notice (2026-10-01): these adapters are unusable. We checked every tensor in all three adapter files (root = seed 42,
adapter_seed_123,adapter_seed_999): all 448 tensors in each file contain NaN, so any model loaded with them returns NaN outputs. Training logs show a mean training loss near 12, consistent with a diverged run. The training data is not documented here, and no generation or safety evaluation exists. Not medical advice. Check script and results: https://github.com/yogvidwankhede/HealthMate-AI/tree/main/paper (paper/check_adapters.py).
LoRA adapters fine-tuned on medical instruction data for the HealthMate-AI project (a medical RAG chatbot). The base model is mistralai/Mistral-7B-Instruct-v0.2; only adapter weights are stored in this repo.
Three adapters trained with identical hyperparameters but different random seeds are included, for robustness/variance analysis:
| Adapter | Location |
|---|---|
| Seed 42 (default) | repo root |
| Seed 123 | adapter_seed_123/ |
| Seed 999 | adapter_seed_999/ |
q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projfrom transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained(
"mistralai/Mistral-7B-Instruct-v0.2", device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("yogvidwankhede/healthmate-mistral-7b-medical-lora")
# Seed 42 adapter (repo root)
model = PeftModel.from_pretrained(base, "yogvidwankhede/healthmate-mistral-7b-medical-lora")
# Or a specific seed:
# model = PeftModel.from_pretrained(base, "yogvidwankhede/healthmate-mistral-7b-medical-lora", subfolder="adapter_seed_123")
Research/educational use as part of a retrieval-augmented medical assistant. Not a substitute for professional medical advice, diagnosis, or treatment. Outputs may be inaccurate; always verify with qualified healthcare professionals.