Edit model card

image/png

adapter_config.json은 λ¨Έμ‹  λŸ¬λ‹μ—μ„œ μ–΄λŒ‘ν„°(Adapter) λͺ¨λΈμ„ κ΅¬μ„±ν•˜κΈ° μœ„ν•œ 섀정을 λ‹΄κ³  μžˆλŠ” JSON νŒŒμΌμž…λ‹ˆλ‹€. μ–΄λŒ‘ν„°λŠ” 사전 ν›ˆλ ¨λœ λͺ¨λΈμ— μΆ”κ°€ν•˜μ—¬ λͺ¨λΈμ˜ 일뢀λ₯Ό 적은 계산 λΉ„μš©μœΌλ‘œ μˆ˜μ •ν•  수 있게 ν•˜λŠ” λͺ¨λ“ˆμž…λ‹ˆλ‹€. 이 μ„€μ • νŒŒμΌμ—λŠ” μ–΄λŒ‘ν„° λ ˆμ΄μ–΄μ˜ 차원, ν•™μŠ΅λ₯ , ν™œμ„±ν™” ν•¨μˆ˜ λ“±μ˜ μ–΄λŒ‘ν„°μ— κ΄€ν•œ ꡬ성 μ˜΅μ…˜μ΄ 포함될 수 μžˆμŠ΅λ‹ˆλ‹€.

True Positives (TP): 257개의 μƒ˜ν”Œμ΄ κΈμ •μœΌλ‘œ μ˜¬λ°”λ₯΄κ²Œ λΆ„λ₯˜λ˜μ—ˆμŠ΅λ‹ˆλ‹€. True Negatives (TN): 284개의 μƒ˜ν”Œμ΄ λΆ€μ •μœΌλ‘œ μ˜¬λ°”λ₯΄κ²Œ λΆ„λ₯˜λ˜μ—ˆμŠ΅λ‹ˆλ‹€. False Positives (FP): 208개의 μƒ˜ν”Œμ΄ λΆ€μ •μž„μ—λ„ λΆˆκ΅¬ν•˜κ³  κΈμ •μœΌλ‘œ 잘λͺ» λΆ„λ₯˜λ˜μ—ˆμŠ΅λ‹ˆλ‹€. False Negatives (FN): 251개의 μƒ˜ν”Œμ΄ κΈμ •μž„μ—λ„ λΆˆκ΅¬ν•˜κ³  λΆ€μ •μœΌλ‘œ 잘λͺ» λΆ„λ₯˜λ˜μ—ˆμŠ΅λ‹ˆλ‹€. 정확도(Accuracy): μ •ν™•λ„λŠ” (TP + TN) / (TP + TN + FP + FN)으둜 κ³„μ‚°λ˜λ©°, 이 κ²½μš°μ—λŠ” 54.1%둜 κ³„μ‚°λ©λ‹ˆλ‹€. 이 μ •ν™•λ„λŠ” λͺ¨λΈμ΄ λΆ„λ₯˜ μž‘μ—…μ„ μˆ˜ν–‰ν•˜λŠ” 데 μžˆμ–΄ 쀑간 μ •λ„μ˜ μ„±λŠ₯을 보여쀀닀고 ν•  수 μžˆμŠ΅λ‹ˆλ‹€. 일반적으둜 λΆ„λ₯˜ λͺ¨λΈμ˜ 정확도가 50%λ₯Ό 쑰금 λ„˜μœΌλ©΄ λ¬΄μž‘μœ„ μΆ”μΈ‘λ³΄λ‹€λŠ” λ‚«μ§€λ§Œ, μ—¬μ „νžˆ λ§Žμ€ κ°œμ„ μ΄ ν•„μš”ν•¨μ„ μ˜λ―Έν•©λ‹ˆλ‹€. 특히, FNκ³Ό FPκ°€ 높은 경우, λͺ¨λΈμ΄ νŠΉμ • 클래슀λ₯Ό λΆ„λ₯˜ν•˜λŠ” 데 λ¬Έμ œκ°€ μžˆμŒμ„ λ‚˜νƒ€λƒ…λ‹ˆλ‹€.

NSMC(Naver Sentiment Movie Corpus): 'nsmc'λŠ” 넀이버 μ˜ν™” 리뷰에 λŒ€ν•œ 감정 뢄석을 μœ„ν•œ λ°μ΄ν„°μ…‹μœΌλ‘œ, λŒ€λž΅ 20만 개의 리뷰둜 κ΅¬μ„±λ˜μ–΄ 있으며 각 λ¦¬λ·°μ—λŠ” 긍정 ν˜Ήμ€ λΆ€μ •μ˜ λ ˆμ΄λΈ”μ΄ μ§€μ •λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€. 데이터 μ‚¬μš©: 이 데이터셋은 주둜 ν•œκ΅­μ–΄ ν…μŠ€νŠΈμ˜ 감정 뢄석을 μœ„ν•΄ μ‚¬μš©λ˜λ©°, λͺ¨λΈμ΄ μžμ—°μ–΄ 이해 λŠ₯λ ₯을 ν•™μŠ΅ν•˜κ³  κ²€μ¦ν•˜λŠ” 데 μœ μš©ν•©λ‹ˆλ‹€. ν›ˆλ ¨ λ°μ΄ν„°λŠ” 'train' λΆ€λΆ„μ˜ 첫 2000개 μƒ˜ν”Œμ„, ν…ŒμŠ€νŠΈ λ°μ΄ν„°λŠ” 'test' λΆ€λΆ„μ˜ 첫 1000개 μƒ˜ν”Œμ„ μ‚¬μš©ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€.

ν…ŒμŠ€νŠΈ 쑰건: μ‹œν€€μŠ€ 길이: ν…μŠ€νŠΈμ˜ μž…λ ₯ μ‹œν€€μŠ€ κΈΈμ΄λŠ” μ½”λ“œμ— 따라 μ„€μ •ν•  수 μžˆμœΌλ‚˜, GPU λ©”λͺ¨λ¦¬ λΆ€μ‘±μœΌλ‘œ 200κ³Ό 같이 μ„€μ •ν–ˆμŠ΅λ‹ˆλ‹€. 배치 μ‚¬μ΄μ¦ˆ: ν•™μŠ΅κ³Ό 평가에 μ‚¬μš©λ˜λŠ” 배치 μ‚¬μ΄μ¦ˆλŠ” 각각 1둜 μ„€μ •λ˜μ–΄ 있으며, μ΄λŠ” 맀우 μž‘μ€ ν¬κΈ°μž…λ‹ˆλ‹€. κ·ΈλΌλ””μ–ΈνŠΈ 좕적: λͺ¨λΈμ€ κ·ΈλΌλ””μ–ΈνŠΈλ₯Ό 2개의 μŠ€ν…λ§ˆλ‹€ μΆ•μ ν•©λ‹ˆλ‹€. ν•™μŠ΅λ₯ : κΈ°λ³Έ μ„€μ •μœΌλ‘œλŠ” 1e-4의 ν•™μŠ΅λ₯ μ„ μ‚¬μš©ν•˜λ©°, 코사인 ν•™μŠ΅λ₯  μŠ€μΌ€μ€„λŸ¬(cosine learning rate scheduler)λ₯Ό μ‚¬μš©ν•©λ‹ˆλ‹€. 에포크: λͺ¨λΈμ€ ν•œ 에포크(epoch) λ™μ•ˆ ν›ˆλ ¨λ©λ‹ˆλ‹€. μ΅œμ ν™”κΈ°: νŽ˜μ΄μ§€λœ μ•„λ‹΄W 32λΉ„νŠΈ(paged_adamw_32bit) μ΅œμ ν™”κΈ°λ₯Ό μ‚¬μš©ν•©λ‹ˆλ‹€. 정밀도: λͺ¨λΈμ€ λ°˜μ •λ°€λ„(fp16)λ₯Ό μ‚¬μš©ν•˜μ—¬ ν•™μŠ΅ν•©λ‹ˆλ‹€.

Model Card for Model ID

Model Details

Model Description

  • Developed by: [More Information Needed]
  • Funded by [optional]: [More Information Needed]
  • Shared by [optional]: [More Information Needed]
  • Model type: [More Information Needed]
  • Language(s) (NLP): [More Information Needed]
  • License: [More Information Needed]
  • Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

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

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

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

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

  • Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

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]

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • llm_int8_threshold: 6.0
  • llm_int8_skip_modules: None
  • llm_int8_enable_fp32_cpu_offload: False
  • llm_int8_has_fp16_weight: False
  • bnb_4bit_quant_type: nf4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.7.0
Downloads last month
5
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for cheonyumin/lora-llama-2-7b-food-order-understanding

Adapter
(1037)
this model