Llama-3.2-3B-Reasoning-Vi-Medical-LoRA

2
3 languages
base_model:meta-llama/Llama-3.2-3B-Instruct
by
danhtran2mind
Other
OTHER
3B params
New
2 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
7GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
3GB+ RAM

Training Data Analysis

🟡 Average (4.8/10)

Researched training datasets used by Llama-3.2-3B-Reasoning-Vi-Medical-LoRA with quality assessment

Specialized For

general
science
multilingual
reasoning

Training Datasets (4)

common crawl
🔴 2.5/10
general
science
Key Strengths
  • Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
  • Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
  • Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
  • Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
  • Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
c4
🔵 6/10
general
multilingual
Key Strengths
  • Scale and Accessibility: 750GB of publicly available, filtered text
  • Systematic Filtering: Documented heuristics enable reproducibility
  • Language Diversity: Despite English-only, captures diverse writing styles
Considerations
  • English-Only: Limits multilingual applications
  • Filtering Limitations: Offensive content and low-quality text remain despite filtering
wikipedia
🟡 5/10
science
multilingual
Key Strengths
  • High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
  • Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
  • Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
  • Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
  • Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
🟡 5.5/10
science
reasoning
Key Strengths
  • Scientific Authority: Peer-reviewed content from established repository
  • Domain-Specific: Specialized vocabulary and concepts
  • Mathematical Content: Includes complex equations and notation
Considerations
  • Specialized: Primarily technical and mathematical content
  • English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Training procedurepython
import os
from huggingface_hub import login

# Set the Hugging Face API token
os.environ["HUGGINGFACEHUB_API_TOKEN"] = "<your_huggingface_token>"

# # Initialize API
login(os.environ.get("HUGGINGFACEHUB_API_TOKEN"))
Set the Hugging Face API tokenpythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

device = "cuda" if torch.cuda.is_available() else "cpu"

# Define model and LoRA adapter paths
base_model_name = "unsloth/Llama-3.2-3B-Instruct"
lora_adapter_name = "danhtran2mind/Llama-3.2-3B-Reasoning-Vi-Medical-LoRA"

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_name)

# Load base model with optimized settings
model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype=torch.float16,  # Use FP16 for efficiency
    device_map=device,
    trust_remote_code=True
)

# Apply LoRA adapter
model = PeftModel.from_pretrained(model, lora_adapter_name)

# Set model to evaluation mode
model.eval()

inference_prompt_style = """Bên dưới là một hướng dẫn mô tả một tác vụ, đi kèm với một thông tin đầu vào để cung cấp thêm ngữ cảnh.
Hãy viết một phản hồi để hoàn thành yêu cầu một cách phù hợp.
Trước khi trả lời, hãy suy nghĩ cẩn thận về câu hỏi và tạo một chuỗi suy nghĩ từng bước để đảm bảo phản hồi logic và chính xác.

### Instruction:
Bạn là một chuyên gia y tế có kiến thức chuyên sâu về lập luận lâm sàng, chẩn đoán và lập kế hoạch điều trị.
Vui lòng trả lời câu hỏi y tế sau đây.

### Question:
{}

### Response:
<think>
"""

# Define the question
question = ("Khi nghi ngờ bị loét dạ dày tá tràng nên đến khoa nào "
            "tại bệnh viện để thăm khám?")

seed = 42
torch.manual_seed(seed)
if torch.cuda.is_available():
    torch.cuda.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)

inputs = tokenizer(
    [inference_prompt_style.format(question) + tokenizer.eos_token],
    return_tensors="pt"
).to(device)

outputs = model.generate(
    **inputs,
    max_new_tokens=2048,
    temperature=0.7,
    top_p=0.95,
    top_k=64,
)

response = tokenizer.batch_decode(outputs, skip_special_tokens=True)
print(response[0].split("### Response:")[1])

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.