GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MOHAMMED7M7
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
MOHAMMED7M7
Model Tree
Input Modalities
Output Modalities
Supported Functionality
AI Doctor V1 is an advanced medical language model fine-tuned for clinical reasoning, diagnostic support, and treatment planning. Built on state-of-the-art transformer architecture and trained on medical reasoning datasets, this model demonstrates strong capabilities in understanding complex medical scenarios and providing structured clinical insights.
notebook
# Core libraries !pip install unsloth # install unsloth!pip install --force-reinstall --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git # Also get the latest version Unsloth! !pip install torch torchaudio transformers accelerate!pip install trl datasets huggingface_hub wandb # Quantization and optimization# Install bitsandbytes!pip install -U bitsandbytes # Optional: For better performance!pip install sentencepiece protobufnotebook
from unsloth import FastLanguageModelimport torchfrom trl import SFTTrainerfrom unsloth import is_bfloat16_supportedfrom huggingface_hub import loginfrom transformers import TrainingArgumentsfrom datasets import load_datasetimport wandbnotebook
from google.colab import userdatahf_token = userdata.get('HF_TOKEN')login(hf_token)notebook
import torchprint("CUDA available:", torch.cuda.is_available())print("GPU device:", torch.cuda.get_device_name(0) if torch.cuda.is_available() else "No GPU")notebook
model_name = "NeoAivara/AI_Doctor_V1"max_sequence_length = 2048dtype = Noneload_in_4bit = True model, tokenizer = FastLanguageModel.from_pretrained( model_name = model_name, max_seq_length = max_sequence_length, dtype = dtype, load_in_4bit = load_in_4bit, token = hf_token)notebook
prompt = f"### Question: {question}\n### Answer:"notebook
# Define a test questionquestion = """What are the common symptoms of pneumonia?""" FastLanguageModel.for_inference(model_lora) # Tokenize the inputinputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda") # Generate a responseoutputs = model_lora.generate ( input_ids = inputs.input_ids, attention_mask = inputs.attention_mask, max_new_tokens = 1200, use_cache = True) # Decode the response tokens back to textresponse = tokenizer.batch_decode(outputs)answer = response.split("### Answer:")[-1].strip() print(answer)python
question = "A patient presents with fever, cough, and night sweats for 3 weeks. What should be considered?"python
question = "What is the first-line treatment for uncomplicated community-acquired pneumonia in adults?"python
question = "Explain the diagnostic approach for a patient with suspected acute appendicitis."python
question = "Explain the pathophysiology of type 2 diabetes mellitus."Recommended parameters for different use cases:
| Parameter | Diagnostic | Educational | Treatment Planning |
|---|---|---|---|
temperature | 0.5-0.7 | 0.7-0.8 | 0.6-0.7 |
top_p | 0.85-0.9 | 0.9-0.95 | 0.85-0.9 |
max_new_tokens | 512-768 | 768-1024 | 512-768 |
repetition_penalty | 1.1 | 1.0 | 1.1 |
🚨 CRITICAL: FOR RESEARCH AND EDUCATIONAL PURPOSES ONLY 🚨
This AI model is designed for:
This AI model is NOT intended for:
Contributions to improve the model, documentation, or use cases are welcome. Please ensure all contributions maintain the educational and research focus of this project.
This model is released under the Apache 2.0 License. See LICENSE file for details.
For questions, issues, or collaboration inquiries, please open an issue on the model repository.
Remember: AI is a tool to augment, not replace, human medical expertise.
Always prioritize patient safety and professional medical judgment.
# Core libraries!pip install unsloth # install unsloth!pip install --force-reinstall --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git # Also get the latest version Unsloth!!pip install torch torchaudio transformers accelerate!pip install trl datasets huggingface_hub wandb# Quantization and optimization# Install bitsandbytes!pip install -U bitsandbytes# Optional: For better performance!pip install sentencepiece protobuffrom unsloth import FastLanguageModelimport torchfrom trl import SFTTrainerfrom unsloth import is_bfloat16_supportedfrom huggingface_hub import loginfrom transformers import TrainingArgumentsfrom datasets import load_datasetimport wandbimport torchprint("CUDA available:", torch.cuda.is_available())print("GPU device:", torch.cuda.get_device_name(0) if torch.cuda.is_available() else "No GPU")model_name = "NeoAivara/AI_Doctor_V1"max_sequence_length = 2048dtype = Noneload_in_4bit = Truemodel, tokenizer = FastLanguageModel.from_pretrained( model_name = model_name, max_seq_length = max_sequence_length, dtype = dtype, load_in_4bit = load_in_4bit, token = hf_token)# Define a test questionquestion = """What are the common symptoms of pneumonia?"""FastLanguageModel.for_inference(model_lora)# Tokenize the inputinputs = tokenizer([prompt_style.format(question, "")], return_tensors="pt").to("cuda")# Generate a responseoutputs = model_lora.generate ( input_ids = inputs.input_ids, attention_mask = inputs.attention_mask, max_new_tokens = 1200, use_cache = True)# Decode the response tokens back to textresponse = tokenizer.batch_decode(outputs)answer = response.split("### Answer:")[-1].strip()print(answer)