初始化项目，由ModelHub XC社区提供模型
Model: cywellai/privacy-counsel-ko-8b Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
511
README.md
Normal file
511
README.md
Normal file
@@ -0,0 +1,511 @@
|
||||
---
|
||||
language:
|
||||
- ko
|
||||
tags:
|
||||
- legal
|
||||
- privacy
|
||||
- korean-law
|
||||
- pipa
|
||||
- isms-p
|
||||
- qwen
|
||||
- sft
|
||||
- consulting
|
||||
- lora
|
||||
- peft
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
datasets:
|
||||
- custom
|
||||
metrics:
|
||||
- custom
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
model-index:
|
||||
- name: privacy-counsel-ko-8b
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: PIPA Consulting Q&A (5-Axis Structured)
|
||||
dataset:
|
||||
type: custom
|
||||
name: Internal Gold Set (150 questions)
|
||||
metrics:
|
||||
- type: custom
|
||||
name: Total Score (0-15, 5-axis)
|
||||
value: 14.38
|
||||
- type: custom
|
||||
name: Structure (0-3)
|
||||
value: 2.96
|
||||
- type: custom
|
||||
name: Legal Articles (0-3)
|
||||
value: 2.66
|
||||
- type: custom
|
||||
name: Internal Structure (0-3)
|
||||
value: 2.95
|
||||
- type: custom
|
||||
name: Practical Measures (0-3)
|
||||
value: 2.93
|
||||
- type: custom
|
||||
name: Expression Quality (0-3)
|
||||
value: 2.87
|
||||
- type: custom
|
||||
name: Gold Pass Rate
|
||||
value: 0.96
|
||||
---
|
||||
|
||||
# privacy-counsel-ko-8b (v4-rebalanced)
|
||||
|
||||
> Korean PIPA (Personal Information Protection Act) consulting LoRA adapter for Qwen3-8B, trained on 9,009 curated legal Q&A samples with 5-stage validation pipeline.
|
||||
|
||||
한국 **개인정보 보호법(PIPA)** 실무 Q&A에 최적화된 Qwen3-8B 기반 LoRA 파인튜닝 모델입니다.
|
||||
답변은 `[판단] → [법적 근거] → [실무 조치] → [추가확인질문]` 4단 구조를 따르며,
|
||||
[법적 근거] 내부에 `원칙 → 조건(트리거) → 예외` 3단 구조를 사용합니다.
|
||||
|
||||
> **Best config:** `temperature=0.5`, `repetition_penalty=1.0`
|
||||
> **Score:** **14.38 / 15** (5축), **Gold 144/150** (96.0%)
|
||||
> **Evaluation:** 2026-02-27 · 150-question gold set · 5-axis scoring v2.1
|
||||
|
||||
---
|
||||
|
||||
## 주요 특징
|
||||
|
||||
* **Qwen3-8B** 기반 LoRA SFT (r=64, α=128, 7개 target modules)
|
||||
* **개인정보보호법 특화**: 9,009건 한국어 법률 Q&A 데이터로 학습 (품질 기반 리밸런싱)
|
||||
* **5단 자동 검증 파이프라인**: 구조/조문/수치/금지패턴/도메인격리 자동 검수
|
||||
* **원칙-조건-예외 3단 구조**: 법적 판단의 조건부 뉘앙스를 체계적으로 전달
|
||||
* **상용 API 대비 압도적 우위**: GPT-4o(7.99) 대비 +6.39점 (task-specific)
|
||||
|
||||
---
|
||||
|
||||
## 성능
|
||||
|
||||
### 5축 15점 평가 (150건 골드셋)
|
||||
|
||||
| 순위 | 모델 | 유형 | 총점/15 | 구조 | 법조항 | 내부 | 실무 | 표현 | Gold | Silver | Fail |
|
||||
|:---:|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
||||
| ※ | **Claude Opus 4.6** ¹ | 참조 | **15.00** | 3.00 | 3.00 | 3.00 | 3.00 | 3.00 | 150 | 0 | 0 |
|
||||
| 1 | **v4-rebalanced** | SFT | **14.38** | 2.96 | 2.66 | 2.95 | 2.93 | 2.87 | **144** | 2 | 4 |
|
||||
| 2 | v4 | SFT | 13.74 | 3.00 | 2.17 | 2.99 | 3.00 | 2.59 | 123 | 26 | 0 |
|
||||
| 3 | v3.1 | SFT | 13.21 | 2.99 | 2.19 | 2.95 | 2.98 | 2.10 | 97 | 52 | 1 |
|
||||
| 4 | v4-full | SFT | 12.65 | 3.00 | 2.23 | 3.00 | 3.00 | 1.42 | 67 | 82 | 1 |
|
||||
| 5 | v3 | SFT | 12.23 | 3.00 | 2.06 | 2.96 | 2.88 | 1.33 | 39 | 98 | 3 |
|
||||
| 6 | Qwen3-8B Base | Base | 10.01 | 2.92 | 2.46 | 0.32 | 2.11 | 2.19 | 14 | 1 | 60 |
|
||||
| 7 | GPT-4o ² | API | 7.99 | 3.00 | 2.81 | 0.00 | 1.79 | 1.31 | 0 | 0 | 138 |
|
||||
| 8 | Solar Pro ² | API | 7.99 | 2.91 | 2.15 | 0.00 | 1.89 | 1.04 | 0 | 0 | 142 |
|
||||
| 9 | Gemini Pro ² | API | 7.71 | 1.99 | 2.72 | 0.00 | 2.00 | 1.00 | 0 | 0 | 145 |
|
||||
|
||||
¹ **Claude Opus 4.6**: 채점 기준의 상한(reference oracle). 비교 대상이 아닌 참조 기준.
|
||||
² **상용 API 모델**: 본 평가는 한국 개인정보보호법 도메인 전문성과 특정 출력 형식을 동시에 요구하는 task-specific 벤치마크입니다. 내부구조 0점은 원칙/조건/예외 패턴이 프롬프트만으로 출력되지 않기 때문이며, 해당 모델들의 범용 능력과 직접 비교할 수 없습니다.
|
||||
|
||||
### 채점 기준 (5축 v2.1)
|
||||
|
||||
| 축 | 0점 | 1점 | 2점 | 3점 |
|
||||
|:--:|------|------|------|------|
|
||||
| **구조** | 섹션 없음 | 1-2섹션 | 3섹션 또는 금지섹션 포함 | 4섹션 완전 + 금지섹션 없음 |
|
||||
| **법조항** | 없음 | 제N조 존재 | 풀인용(OO법 제N조) | 풀인용 + MIN_CORE 정합 + 시행령 |
|
||||
| **내부구조** | 없음 | 1-2개 | 원칙/조건/예외 3개 | 3개 + 예외 실질 내용 |
|
||||
| **실무** | 없음 | 액션 1-2개 | 액션 3개+ | 즉시/단기/재발방지 3단계 + 액션 3개+ |
|
||||
| **표현** | 금지패턴+CJK | 금지패턴 없음 | 조건부 secondary | 조건부 primary(다만) + 무오염 |
|
||||
|
||||
> **Gold:** ≥12.5/15 AND 전 게이트 통과 · **Silver:** ≥11.5 · **Bronze:** ≥10.0
|
||||
> 내부 개발 과정에서는 3축 9점(구조/정확/실무) 스케일도 병행 운용하며, 두 스케일 간 직접 환산 관계는 없습니다.
|
||||
|
||||
### v4-rebalanced 도메인별 성능
|
||||
|
||||
| 도메인 | 문항 | 총점/15 | 구조 | 법조항 | 내부 | 실무 | 표현 | Gold | 시행령 | 다만 |
|
||||
|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
||||
| 국외이전 | 20 | **14.75** | 3.00 | 2.75 | 3.00 | 3.00 | 3.00 | 20/20 | 75% | 100% |
|
||||
| 위탁_처리 | 25 | 14.48 | 3.00 | 2.60 | 3.00 | 3.00 | 2.88 | 24/25 | 68% | 100% |
|
||||
| 유출_대응 | 30 | 14.43 | 3.00 | 2.63 | 3.00 | 3.00 | 2.80 | 30/30 | 63% | 90% |
|
||||
| 제3자_제공 | 25 | 14.40 | 3.00 | 2.48 | 3.00 | 3.00 | 2.92 | 24/25 | 48% | 96% |
|
||||
| 기타 ³ | 20 | 14.30 | 2.90 | 2.85 | 2.90 | 2.85 | 2.80 | 18/20 | 85% | 90% |
|
||||
| 동의_수집 | 30 | 14.03 | 2.87 | 2.70 | 2.83 | 2.77 | 2.87 | 28/30 | 70% | 93% |
|
||||
|
||||
³ 기타: 파기, 안전조치, CCTV, 정보주체 권리, ISMS-P, 거버넌스, 벌칙 등 포함
|
||||
|
||||
### 품질 메트릭 (모델 출력 기준)
|
||||
|
||||
| 모델 | 유형 | 평균길이 | 시행령% | 다만% | 내부구조% | 3단계% | 금지패턴 |
|
||||
|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|
||||
| Claude Opus 4.6 | 참조 | 600 | 100% | 100% | 100% | 100% | 0건 |
|
||||
| **v4-rebalanced** | SFT | 721 | **67%** | **95%** | **98%** | **98%** | 1건 |
|
||||
| v4 | SFT | 615 | 17% | 78% | 99% | 100% | 1건 |
|
||||
| v3.1 | SFT | 505 | 19% | 49% | 98% | 99% | 0건 |
|
||||
| v4-full | SFT | 494 | 23% | 13% | 100% | 100% | 1건 |
|
||||
| v3 | SFT | 517 | 9% | 9% | 99% | 100% | 1건 |
|
||||
| Qwen3-8B Base | Base | 1255 | 77% | 70% | 11% | 95% | 20건 |
|
||||
| GPT-4o | API | 760 | 45% | 70% | 0% | 0% | 29건 |
|
||||
| Solar Pro | API | 1409 | 30% | 29% | 0% | 0% | 53건 |
|
||||
| Gemini Pro | API | 1522 | 35% | 25% | 0% | 0% | 42건 |
|
||||
|
||||
> 시행령%: 관련 시행령 동시 인용 비율, 다만%: 조건부 표현("다만,") 포함 비율, 내부구조%: 원칙/조건/예외 3단 포함 비율, 3단계%: 즉시/단기/재발방지 구분 비율
|
||||
|
||||
---
|
||||
|
||||
## 사용법
|
||||
|
||||
### 설치
|
||||
|
||||
```bash
|
||||
pip install transformers torch accelerate
|
||||
# LoRA adapter 직접 로드 시:
|
||||
pip install peft
|
||||
```
|
||||
|
||||
### 추론 (Merged 모델)
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "cywellai/privacy-counsel-ko-8b"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype="bfloat16",
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
|
||||
SYSTEM_PROMPT = """당신은 대한민국 개인정보보호법 전문 상담사입니다.
|
||||
질문에 대해 [판단], [법적 근거], [실무 조치], [추가확인질문] 형식으로 구조화된 답변을 제공합니다.
|
||||
모든 답변은 관련 법조항을 정확히 인용하고, 조건부 표현을 사용하여 법적 판단의 뉘앙스를 전달합니다."""
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": SYSTEM_PROMPT},
|
||||
{"role": "user", "content": "소규모 온라인 쇼핑몰에서 고객 이름과 전화번호를 수집하려 합니다. 어떤 절차가 필요한가요?"},
|
||||
]
|
||||
|
||||
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
inputs = tokenizer(text, return_tensors="pt").to(model.device)
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=1500,
|
||||
temperature=0.5,
|
||||
top_p=0.9,
|
||||
repetition_penalty=1.0,
|
||||
do_sample=True,
|
||||
)
|
||||
|
||||
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### 추론 (LoRA 어댑터)
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
from peft import PeftModel
|
||||
|
||||
base_model_name = "Qwen/Qwen3-8B"
|
||||
adapter_name = "cywellai/privacy-counsel-ko-8b-lora"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(base_model_name, trust_remote_code=True)
|
||||
base_model = AutoModelForCausalLM.from_pretrained(
|
||||
base_model_name,
|
||||
torch_dtype="bfloat16",
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model = PeftModel.from_pretrained(base_model, adapter_name)
|
||||
|
||||
# 이후 동일한 방식으로 추론
|
||||
```
|
||||
|
||||
### vLLM 추론 (권장)
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
llm = LLM(
|
||||
model="cywellai/privacy-counsel-ko-8b",
|
||||
trust_remote_code=True,
|
||||
max_model_len=2048,
|
||||
gpu_memory_utilization=0.5,
|
||||
)
|
||||
|
||||
sampling = SamplingParams(temperature=0.5, repetition_penalty=1.0, max_tokens=1500)
|
||||
|
||||
# tokenizer.apply_chat_template()으로 프롬프트 구성 후
|
||||
outputs = llm.generate([prompt], sampling)
|
||||
print(outputs[0].outputs[0].text)
|
||||
```
|
||||
|
||||
### 추론 파라미터 가이드
|
||||
|
||||
| 파라미터 | 권장 값 | 비고 |
|
||||
|:---|:---:|:---|
|
||||
| temperature | **0.5** | 최적 균형 (0.3: 보수적, 0.7+: 정확도 하락) |
|
||||
| repetition_penalty | **1.0** | 1.15는 정확도 순손실 |
|
||||
| top_p | 0.9 | 표준 설정 |
|
||||
| max_new_tokens | 1500 | 평균 응답 ~720자 |
|
||||
|
||||
---
|
||||
|
||||
## 출력 형식
|
||||
|
||||
아래 시스템 프롬프트와 함께 사용할 때 4단 구조가 안정적으로 출력됩니다.
|
||||
시스템 프롬프트 없이도 4섹션이 출력되는 경우가 있으나, 최적 결과를 위해 시스템 프롬프트 사용을 권장합니다.
|
||||
|
||||
```
|
||||
[판단]
|
||||
개인정보 수집 시 정보주체에게 고지해야 하는 필수 항목은 수집 목적, 수집 항목,
|
||||
보유 및 이용 기간, 동의 거부권 및 거부 시 불이익 등을 포함해야 합니다.
|
||||
|
||||
[법적 근거]
|
||||
• 원칙: 개인정보 보호법 제15조(개인정보의 수집·이용)에 따라 개인정보를
|
||||
수집하거나 이용할 때 정보주체에게 고지해야 합니다.
|
||||
• 조건(트리거): 수집 목적, 수집 항목, 보유 및 이용 기간, 동의 거부권 및
|
||||
거부 시 불이익 등의 내용을 명확히 고지해야 합니다.
|
||||
(개인정보 보호법 제15조, 시행령 제17조)
|
||||
• 예외/주의: 다만, 법률에 특별한 규정이 있는 경우나 정보주체의 권리·이익을
|
||||
침해하지 않는 범위에서 고지를 생략할 수 있습니다.
|
||||
|
||||
[실무 조치]
|
||||
• 즉시: 수집 목적, 항목, 보유기간, 동의 거부권 등의 내용을 문서화하여 준비
|
||||
• 단기: 정보주체에게 해당 내용을 명확히 고지하고 동의를 받음
|
||||
• 재발방지: 개인정보 수집 및 이용 절차를 정기적으로 검토하고 필요 시 개선
|
||||
|
||||
[추가확인질문]
|
||||
• 수집하려는 개인정보의 종류와 목적은 무엇인가요?
|
||||
• 수집한 개인정보의 보유 및 이용 기간은 어떻게 설정되어 있나요?
|
||||
• 동의 거부 시 정보주체에게 발생할 수 있는 불이익은 무엇인가요?
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 학습 상세
|
||||
|
||||
### 데이터 리밸런싱 전략
|
||||
|
||||
v4-full 학습 데이터(14,088건)에서 품질 기반 필터링과 72B 교사 모델 합성을 거쳐 9,009건으로 리밸런싱했습니다.
|
||||
|
||||
| 품질 지표 | 리밸런싱 전 (14,088건) | 리밸런싱 후 (9,009건) | 변화 |
|
||||
|:---|:---:|:---:|:---|
|
||||
| 시행령 인용 포함 비율 | 10.0% | **47.6%** | +37.6%p |
|
||||
| 다만 패턴 포함 비율 | 16.1% | **56.4%** | +40.3%p |
|
||||
| 3단계 실무 포함 비율 | 18.4% | **60.6%** | +42.2%p |
|
||||
| 풀 법조항 인용 비율 | 46.7% | **96.1%** | +49.4%p |
|
||||
| 법조항 점수 (5축) | 2.17 (v4) | **2.66** | +0.49 |
|
||||
| 표현 점수 (5축) | 2.59 (v4) | **2.87** | +0.28 |
|
||||
|
||||
### 모델 개요
|
||||
|
||||
| 항목 | 내용 |
|
||||
|------|------|
|
||||
| **베이스 모델** | [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) (원본 사전학습 모델) |
|
||||
| **학습 방식** | LoRA (BF16 full precision, rank=64) |
|
||||
| **학습 가능 파라미터** | 174.6M / 8.37B (2.09%) |
|
||||
| **학습 데이터** | 9,009건 (품질 기반 리밸런싱 + 72B 합성) |
|
||||
| **검증 데이터** | 900건 (층화 샘플링 재구축) |
|
||||
| **학습 시간** | ~70분 (NVIDIA H200 143GB) |
|
||||
| **최종 평가 손실** | 0.3737 |
|
||||
| **토큰 정확도** | 88.82% |
|
||||
| **라이선스** | Apache 2.0 (Qwen3 라이선스 준수) |
|
||||
|
||||
### LoRA 설정
|
||||
|
||||
| 항목 | 값 |
|
||||
|:---|:---|
|
||||
| LoRA rank | 64 |
|
||||
| LoRA alpha | 128 |
|
||||
| LoRA dropout | 0.05 |
|
||||
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
|
||||
| Trainable params | ~174M / 8B (2.2%) |
|
||||
|
||||
### 학습 파라미터
|
||||
|
||||
| 항목 | 값 |
|
||||
|:---|:---|
|
||||
| Base model | Qwen/Qwen3-8B (원본 사전학습 모델) |
|
||||
| Learning rate | 5e-5 (cosine scheduler, warmup 10%) |
|
||||
| Epochs | 3 |
|
||||
| Batch size | per_device 8 × gradient_accumulation 4 = **effective 32** |
|
||||
| Max sequence length | 2048 |
|
||||
| Training data | 9,009건 |
|
||||
| Total steps | 846 |
|
||||
| Eval/save | every 200 steps |
|
||||
| Framework | TRL 0.27.0, Transformers 4.57.6, PyTorch 2.6.0 |
|
||||
|
||||
### 학습 데이터 구성
|
||||
|
||||
```
|
||||
train.jsonl (9,009건)
|
||||
├── v3_final 원본 (품질 필터 통과): 5,213건 (57.9%)
|
||||
├── Phase3-v2 합성 (72B 교사 모델): 1,835건 (20.4%)
|
||||
├── Phase3-v3 합성 (72B 교사 모델): 1,524건 (16.9%)
|
||||
└── v4_500 (정확도 타겟 보강): 437건 ( 4.9%)
|
||||
```
|
||||
|
||||
**데이터 파이프라인:**
|
||||
1. **Phase 1+2** — v4-full 14,088건에서 4개 품질 지표로 스코어링 + 거버넌스 다운샘플 → 6,595건 유지
|
||||
2. **Phase 3** — Qwen2.5-72B-Instruct(FP8, vLLM)로 부족 도메인 합성 → 3,743건 생성
|
||||
3. **Phase 4** — 합산(10,338건) + 약칭 정규화
|
||||
4. **Phase 5** — 마크다운 오염 제거, 중국어 잔류 삭제, 중복 제거 → 최종 9,009건
|
||||
|
||||
### 학습 곡선
|
||||
|
||||
| Step | Epoch | Train Loss | Eval Loss | Token Accuracy |
|
||||
|:---:|:---:|:---:|:---:|:---:|
|
||||
| 50 | 0.18 | 1.2361 | - | 72.14% |
|
||||
| 200 | 0.71 | 0.4533 | 0.4662 | 86.39% |
|
||||
| 400 | 1.42 | - | 0.4062 | 87.86% |
|
||||
| 600 | 2.13 | 0.3343 | 0.3817 | 88.58% |
|
||||
| **800** | **2.84** | **0.3245** | **0.3737** | **88.82%** |
|
||||
| 846 (final) | 3.00 | - | 0.3737 | 88.82% |
|
||||
|
||||
### 데이터 품질 관리
|
||||
|
||||
| 단계 | 방법 |
|
||||
|:---|:---|
|
||||
| 자동 검증 | 5단 파이프라인 (구조/조문/수치/금지패턴/도메인격리) |
|
||||
| 조문 검증 | MIN_CORE 필수 조문 + 도메인별 확장 허용 목록 대조 |
|
||||
| 골드셋 누출 차단 | SHA-256 해시 기반 자동 차단 (gold_leak_guard) |
|
||||
| 수동 검수 | 카테고리별 10개씩 = 100개 샘플링 검수 |
|
||||
|
||||
---
|
||||
|
||||
## 아키텍처
|
||||
|
||||
```
|
||||
Architecture: Qwen3ForCausalLM
|
||||
Hidden Size: 4,096
|
||||
Num Layers: 36
|
||||
Attention Heads: 32 (GQA, KV Heads: 8)
|
||||
Head Dimension: 128
|
||||
Intermediate Size: 12,288
|
||||
Activation: SiLU
|
||||
Vocab Size: 151,936
|
||||
Max Position Embeddings: 40,960
|
||||
RoPE Theta: 1,000,000
|
||||
Dtype: bfloat16
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 모델 개발 이력
|
||||
|
||||
본 모델은 다수의 반복 학습을 거친 최종 산출물입니다. 모든 버전은 Qwen3-8B 원본에서 독립적으로 LoRA 학습되었습니다.
|
||||
|
||||
| 버전 | 날짜 | 데이터 | 베이스 모델 | LR | max_seq | 5축 총점 | Gold% |
|
||||
|------|------|:---:|---------|:---:|:---:|:---:|:---:|
|
||||
| v3 | 2026-02-08 | 13,631 | Qwen3-8B | 5e-5 | 1024 | 12.23 | 26% |
|
||||
| v3.1 | 2026-02-10 | 13,631 | Qwen3-8B | 5e-5 | 1024 | 13.21 | 65% |
|
||||
| v4 | 2026-02-23 | 1,491 | v3.1-merged | 3e-5 | 1024 | 13.74 | 82% |
|
||||
| v4-full | 2026-02-23 | 14,088 | Qwen3-8B | 5e-5 | 1024 | 12.65 | 45% |
|
||||
| **v4-rebalanced** | **2026-02-27** | **9,009** | **Qwen3-8B** | **5e-5** | **2048** | **14.38** | **96%** |
|
||||
|
||||
### 모델 진화 추이
|
||||
|
||||
| 전환점 | 총점 변화 | 핵심 원인 |
|
||||
|:---|:---:|:---|
|
||||
| Base → v3 | +2.23 | SFT 형식 학습 (내부구조 0.32→2.96, 실무 2.11→2.88) |
|
||||
| v3 → v3.1 | +0.97 | 표현 품질 향상 (1.33→2.10) |
|
||||
| v3.1 → v4 | +0.53 | 법조항 정확도 + 표현 동시 개선 |
|
||||
| v4 → v4-full | -1.09 | 데이터 확장 시 표현 품질 희석 (2.59→1.42) |
|
||||
| v4 → v4-rebalanced | +0.64 | 리밸런싱 효과 (법조항 +0.49, 표현 +0.28) |
|
||||
|
||||
---
|
||||
|
||||
## 관련 리소스
|
||||
|
||||
* **LoRA 어댑터**: [cywellai/privacy-counsel-ko-8b-lora](https://huggingface.co/cywellai/privacy-counsel-ko-8b-lora) (667MB, PEFT 로드)
|
||||
* **베이스 모델**: [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
|
||||
* **개인정보 보호법**: [법령 전문 (국가법령정보센터)](https://www.law.go.kr)
|
||||
* **개인정보보호위원회**: [PIPC 공식 사이트](https://www.pipc.go.kr)
|
||||
|
||||
---
|
||||
|
||||
## 제한 사항
|
||||
|
||||
**법적 정확도:**
|
||||
- 5축 법조항 점수 2.66/3 — 최대 병목 축. MIN_CORE 정합 + 시행령 동시 인용이 부족한 경우 존재
|
||||
- 모델 출력의 시행령 동시 인용률 67% — 나머지 33%는 본법만 인용
|
||||
- 모델 출력의 조건부 표현("다만,") 포함률 95% — 잔여 5%에서 단정적 표현 발생 가능
|
||||
- 도메인별 편차: 제3자_제공(시행령 48%)이 가장 낮고, 기타(85%)가 가장 높음
|
||||
|
||||
**입력 처리:**
|
||||
- 비표준 약칭(예: "개보법") 사용 시 표준 용어로 정규화 필요
|
||||
- 학습 데이터 기준 시점 이후 법령 개정 사항은 미반영
|
||||
|
||||
**개선 로드맵:**
|
||||
1. 시행령 동시 인용률 67% → 85%+ (P0)
|
||||
2. 법조항 점수 2.66 → 2.85+ (P1)
|
||||
3. 기타 도메인(파기/ISMS-P 등) 세분화 학습 (P2)
|
||||
|
||||
---
|
||||
|
||||
## 하드웨어
|
||||
|
||||
- **학습**: NVIDIA H200 143GB × 1, ~70분 (4,240초)
|
||||
- **추론 (최소)**: GPU VRAM 16GB 이상 (BF16 기준)
|
||||
- **추론 (권장)**: GPU VRAM 24GB 이상
|
||||
|
||||
---
|
||||
|
||||
## 평가 조건
|
||||
|
||||
| 항목 | 값 |
|
||||
|:---|:---|
|
||||
| 골드셋 | 150문항 (유출30, 동의30, 위탁25, 제3자25, 국외20, 기타20) |
|
||||
| 난이도 분포 | 기본 54, 예외 46, 경계 50 |
|
||||
| 내부 모델 생성 설정 | temperature=0.5, repetition_penalty=1.0 |
|
||||
| 채점 모델 | Claude Opus 4.6 (5축 v2.1 rubric) |
|
||||
| 게이트 체크 | 4섹션, 법조항존재, 금지패턴없음, CJK없음, 200자이상 |
|
||||
| Gold 기준 | 총점 ≥12.5/15 AND 전 게이트 통과 |
|
||||
| Silver 기준 | 총점 ≥11.5/15 |
|
||||
| Bronze 기준 | 총점 ≥10.0/15 |
|
||||
|
||||
---
|
||||
|
||||
## Disclaimer
|
||||
|
||||
> **본 모델은 법률 자문을 대체하지 않습니다.**
|
||||
|
||||
이 모델의 출력은 개인정보보호 실무 참고용으로만 사용해야 하며, 법적 구속력이 있는 판단이나 자문을 구성하지 않습니다. 고위험 의사결정(유출 통지·신고, 국외이전 계약, 과징금 대응 등)은 반드시 법률 전문가의 검토를 거쳐야 합니다.
|
||||
|
||||
개인정보 보호법 및 관련 법령은 개정될 수 있으며, 본 모델의 학습 데이터가 최신 법령을 완전히 반영하지 못할 수 있습니다.
|
||||
|
||||
---
|
||||
|
||||
## Safety & Privacy
|
||||
|
||||
- **PII 입력 최소화:** 실명·연락처·주민번호 등은 입력하지 마세요
|
||||
- **사례 데이터 가명/마스킹:** 로그·공유·재학습 시 동일 원칙 적용
|
||||
- **출력 검증 권장:** 고위험 의사결정은 내부 체크리스트로 재검토
|
||||
|
||||
---
|
||||
|
||||
## Changelog
|
||||
|
||||
| 날짜 | 내용 |
|
||||
|------|------|
|
||||
| 2026-02-08 | v3 공개 (13,631건, 12.23/15) |
|
||||
| 2026-02-10 | v3.1 공개 (13.21/15, Gold 65%) |
|
||||
| 2026-02-23 | v4 / v4-full 공개 |
|
||||
| 2026-02-27 | **v4-rebalanced 공개** (14.38/15, Gold 96%) |
|
||||
| 2026-03-01 | Model Card v2: 실제 학습 설정 반영, 5축 9개 모델 비교 통합 |
|
||||
|
||||
---
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{privacy-counsel-ko-8b-v4,
|
||||
title = {privacy-counsel-ko-8b (v4-rebalanced):
|
||||
A Fine-tuned Qwen3-8B for Korean PIPA Consulting},
|
||||
author = {CywellAI},
|
||||
year = {2026},
|
||||
note = {LoRA SFT on Qwen3-8B for Korean Personal Information Protection Act Q\&A.
|
||||
5-axis 15-point evaluation: 14.38/15, Gold 96\% on 150-question gold set.
|
||||
Outperforms GPT-4o, Solar Pro, Gemini Pro on task-specific benchmark.},
|
||||
url = {https://huggingface.co/cywellai/privacy-counsel-ko-8b}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
Apache 2.0 — [Qwen3 라이선스](https://huggingface.co/Qwen/Qwen3-8B) 준수.
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74228340c447a6339affd059b41778c74a52b507bfd453d0c1d00c3c19b02627
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e52c23e9d768b0c0e2df0796024c6cf5bfb02f1560bf2790b674536a73acbfb7
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:934280f873163f72320de034fee632dbb6a30db3f6c8c5d750d9f07a0f9e4d32
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b6f5b85a04fa008a0e850a2807b9d1f59f05ff0cae932254a5af59223e9652f
|
||||
size 1580230264
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8190735360,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user