Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string

Health Recommendation Model

ไธ€ไธชๅŸบไบŽ Qwen3-VL-4B-Instruct ็š„ๅฅๅบทๅนฒ้ข„ๆ–นๆกˆ็”Ÿๆˆๆจกๅž‹ใ€‚

Model Description

่ฟ™ไธชๆจกๅž‹ๆ˜ฏไธ“้—จ้’ˆๅฏนๅฅๅบทๆŽจ่ๅ’Œๅนฒ้ข„ๆ–นๆกˆ็”ŸๆˆไปปๅŠก่ฟ›่กŒๅพฎ่ฐƒ็š„ LoRA ้€‚้…ๅ™จใ€‚ๅฎƒ่ƒฝๅคŸๆ นๆฎ็”จๆˆทๆไพ›็š„็—‡็Šถไฟกๆฏ๏ผŒ็”Ÿๆˆไธชๆ€งๅŒ–็š„ๅฅๅบทๅนฒ้ข„ๆ–นๆกˆ๏ผŒๅŒ…ๆ‹ฌ็”Ÿๆดปๆ–นๅผๅปบ่ฎฎใ€ๅฟƒ็†ๅนฒ้ข„ๅ’Œ็Žฏๅขƒๆ”น้€ ๅปบ่ฎฎใ€‚

ไธป่ฆๅŠŸ่ƒฝ

  • ็—‡็Šถๅˆ†ๆž: ๅŸบไบŽ็”จๆˆทๆไพ›็š„็—‡็Šถไฟกๆฏ่ฟ›่กŒๅˆ†ๆž
  • ๅนฒ้ข„ๆ–นๆกˆ็”Ÿๆˆ: ็”ŸๆˆๅŒ…ๅซ็”Ÿๆดปๆ–นๅผใ€ๅฟƒ็†ใ€็Žฏๅขƒไธ‰ไธช็ปดๅบฆ็š„ๅนฒ้ข„ๅปบ่ฎฎ
  • ็†่ฎบไพๆฎ: ๆ–นๆกˆๅŸบไบŽ P3 ๆก†ๆžถๆˆ– PROCEED ๆก†ๆžถ
  • ่ฏ„ไผฐๆŒ‡ๆ ‡: ๆไพ›ๅฏ้‡ๅŒ–็š„่ฏ„ไผฐๆŒ‡ๆ ‡

ๆจกๅž‹็‰น็‚น

  • Base Model: Qwen/Qwen3-VL-4B-Instruct
  • Fine-tuning Method: LoRA (Low-Rank Adaptation)
  • Language: ไธญๆ–‡ (Chinese)
  • Domain: Healthcare, Health Recommendation

Model Details

Model Description

  • Developed by: oscarzhang
  • Model type: LoRA Adapter for Qwen3-VL-4B-Instruct
  • Language(s): Chinese (ไธญๆ–‡)
  • License: Apache 2.0 (inherited from base model)
  • Finetuned from: Qwen/Qwen3-VL-4B-Instruct

Model Sources [optional]

  • Repository: [More Information Needed]
  • Paper [optional]: [More Information Needed]
  • Demo [optional]: [More Information Needed]

Uses

Direct Use

่ฟ™ไธชๆจกๅž‹ๅฏไปฅ็›ดๆŽฅ็”จไบŽ็”Ÿๆˆๅฅๅบทๅนฒ้ข„ๆ–นๆกˆใ€‚็”จๆˆท้œ€่ฆๆไพ›๏ผš

  • ็ฒ—็—‡็Šถ๏ผˆไธป่ฆ็—‡็Šถๆ่ฟฐ๏ผ‰
  • ็ป†ๅŒ–็—‡็Šถ๏ผˆๅ…ทไฝ“็—‡็Šถ็ป†่Š‚๏ผ‰

ๆจกๅž‹ๅฐ†่พ“ๅ‡บๅŒ…ๅซไปฅไธ‹ๅ†…ๅฎน็š„ๅนฒ้ข„ๆ–นๆกˆ๏ผš

  1. ๆŽจ่ๅนฒ้ข„๏ผš
    • ็”Ÿๆดปๆ–นๅผ๏ผšๅ…ทไฝ“็š„่กŒๅŠจๅปบ่ฎฎ
    • ๅฟƒ็†๏ผšๅฟƒ็†่ฎค็Ÿฅๅฑ‚้ข็š„ๅนฒ้ข„
    • ็Žฏๅขƒ๏ผš็Žฏๅขƒๆ”น้€ ๅปบ่ฎฎ
  2. ่ฏ„ไผฐๆŒ‡ๆ ‡๏ผšๅฏ้‡ๅŒ–ๆต‹้‡็š„ๆŒ‡ๆ ‡

ไฝฟ็”จ็คบไพ‹

from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

# ๅŠ ่ฝฝๅŸบ็ก€ๆจกๅž‹ๅ’Œ้€‚้…ๅ™จ
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-VL-4B-Instruct",
    trust_remote_code=True
)
model = PeftModel.from_pretrained(base_model, "oscarzhang/HealthRecommendation")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-VL-4B-Instruct", trust_remote_code=True)

# ็”Ÿๆˆๅนฒ้ข„ๆ–นๆกˆ
prompt = """่ฏทๅŸบไบŽ็—‡็Šถไฟกๆฏ๏ผŒ็”Ÿๆˆไธชๆ€งๅŒ–็š„ๅฅๅบทๅนฒ้ข„ๆ–นๆกˆใ€‚

็ฒ—็—‡็Šถ๏ผš็–ฒๅŠณ
็ป†ๅŒ–็—‡็Šถ๏ผšๆ—ฉๆ™จ่ตทๅบŠๅŽๆŒ็ปญ็–ฒๆƒซๆ„Ÿ๏ผŒๅฝฑๅ“ๆ—ฅๅธธๅทฅไฝœ"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=500, temperature=0.3)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Downstream Use

่ฟ™ไธชๆจกๅž‹ๅฏไปฅ่ฟ›ไธ€ๆญฅๅพฎ่ฐƒ็”จไบŽ๏ผš

  • ็‰นๅฎš็–พ็—…็š„ๅนฒ้ข„ๆ–นๆกˆ็”Ÿๆˆ
  • ไธๅŒๅนด้พ„ๆฎตไบบ็พค็š„ๅฅๅบทๅปบ่ฎฎ
  • ็ป“ๅˆๆ›ดๅคšๅฅๅบทๆ•ฐๆฎ็š„ๆŽจ่็ณป็ปŸ

Out-of-Scope Use

โš ๏ธ ้‡่ฆ้™ๅˆถ๏ผš

  • ๆœฌๆจกๅž‹ไป…ๆไพ›็”Ÿๆดปๅนฒ้ข„ๅปบ่ฎฎ๏ผŒไธๅšๅŒป็–—่ฏŠๆ–ญ
  • ไธๅบ”็”จไบŽ็ดงๆ€ฅๅŒป็–—ๆƒ…ๅ†ต
  • ๅฏนไบŽ้œ€่ฆๅŒป็–—ๅนฒ้ข„็š„ๆƒ…ๅ†ต๏ผŒๅฟ…้กปๆ˜Ž็กฎๆŒ‡ๅ‡บ้œ€่ฆๅฐฑๅŒป
  • ไธๅบ”ๆ›ฟไปฃไธ“ไธšๅŒป็–—ๅปบ่ฎฎ

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

่ฎญ็ปƒๆ•ฐๆฎๅŒ…ๅซ126ไธชๅฅๅบทๅนฒ้ข„ๆ–นๆกˆๆ ทๆœฌ๏ผŒๆฏไธชๆ ทๆœฌๅŒ…ๅซ๏ผš

  • ็—‡็Šถไฟกๆฏ๏ผˆ็ฒ—็—‡็Šถๅ’Œ็ป†ๅŒ–็—‡็Šถ๏ผ‰
  • ็†่ฎบๆก†ๆžถๅˆ†ๆž๏ผˆP3ๆก†ๆžถๅ’ŒPROCEEDๆก†ๆžถ๏ผ‰
  • ๅฎŒๆ•ด็š„ๅนฒ้ข„ๆ–นๆกˆ๏ผˆ็”Ÿๆดปๆ–นๅผใ€ๅฟƒ็†ใ€็Žฏๅขƒไธ‰ไธช็ปดๅบฆ๏ผ‰
  • ่ฏ„ไผฐๆŒ‡ๆ ‡

Training Procedure

Preprocessing

่ฎญ็ปƒๆ•ฐๆฎ็ป่ฟ‡ไปฅไธ‹้ข„ๅค„็†๏ผš

  • ็—‡็Šถๆ ‡ๅ‡†ๅŒ–
  • ็†่ฎบๆก†ๆžถๆๅ–
  • ๅนฒ้ข„ๆ–นๆกˆ็ป“ๆž„ๅŒ–
  • ่ดจ้‡่ฏ„ๅˆ†้ชŒ่ฏ

Training Hyperparameters

  • Training method: LoRA (Low-Rank Adaptation)
  • Training regime: fp16 mixed precision
  • LoRA rank (r): 16
  • LoRA alpha: 16
  • LoRA dropout: 0.05
  • Target modules: v_proj, q_proj, k_proj, o_proj
  • Learning rate: 2e-4 (with linear decay and warmup)
  • Batch size: 1 (with gradient accumulation of 8)
  • Training steps: 100
  • Max sequence length: 512 tokens

Training Results

  • Initial Loss: 2.5
  • Final Loss: 0.7
  • Loss reduction: 72%
  • Training time: ~1.7 hours

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: [More Information Needed]
  • Hours used: [More Information Needed]
  • Cloud Provider: [More Information Needed]
  • Compute Region: [More Information Needed]
  • Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

  • PEFT 0.17.1
Downloads last month
4
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for oscarzhang/HealthRecommendation

Adapter
(255)
this model

Paper for oscarzhang/HealthRecommendation