初始化项目，由ModelHub XC社区提供模型
Model: twinkle-ai/gemma-3-4B-T1-it Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
tokenizer*.json filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
3
.gitignore
vendored
Normal file
3
.gitignore
vendored
Normal file
@@ -0,0 +1,3 @@
|
||||
.ipynb_checkpoints/
|
||||
__pycache__/
|
||||
*.log
|
||||
396
README.md
Normal file
396
README.md
Normal file
@@ -0,0 +1,396 @@
|
||||
---
|
||||
license: gemma
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
base_model:
|
||||
- google/gemma-3-4b-pt
|
||||
library_name: transformers
|
||||
tags:
|
||||
- Taiwan
|
||||
- R.O.C
|
||||
- zhtw
|
||||
- SLM
|
||||
- Gemma-3
|
||||
- gemma3
|
||||
datasets:
|
||||
- lianghsun/tw-reasoning-instruct
|
||||
- lianghsun/tw-contract-review-chat
|
||||
- minyichen/tw-instruct-R1-200k
|
||||
- minyichen/tw_mm_R1
|
||||
- minyichen/LongPaper_multitask_zh_tw_R1
|
||||
- nvidia/Nemotron-Instruction-Following-Chat-v1
|
||||
|
||||
model-index:
|
||||
- name: gemma-3-4B-T1-it
|
||||
results:
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: ikala/tmmluplus
|
||||
name: tmmlu+
|
||||
config: all
|
||||
split: test
|
||||
revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 47.44
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: cais/mmlu
|
||||
name: mmlu
|
||||
config: all
|
||||
split: test
|
||||
revision: c30699e
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 59.13
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: lianghsun/tw-legal-benchmark-v1
|
||||
name: tw-legal-benchmark-v1
|
||||
config: all
|
||||
split: test
|
||||
revision: 66c3a5f
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 44.18
|
||||
metrics:
|
||||
- accuracy
|
||||
---
|
||||
|
||||
# Model Card for gemma-3-4B-T1-it
|
||||
|
||||
<div align="center" style="line-height: 1;">
|
||||
<a href="https://discord.gg/Cx737yw4ed" target="_blank" style="margin: 2px;">
|
||||
<img alt="Discord"
|
||||
src="https://img.shields.io/badge/Discord-Twinkle%20AI-7289da?style=for-the-badge&logo=discord&logoColor=white"
|
||||
style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
|
||||
<a href="https://huggingface.co/twinkle-ai" target="_blank" style="margin: 2px;">
|
||||
<img alt="Hugging Face"
|
||||
src="https://img.shields.io/badge/Hugging%20Face-Twinkle%20AI-ffc107?style=for-the-badge&logo=huggingface&logoColor=white"
|
||||
style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
|
||||
<a href="https://modelscope.cn/organization/twinkle-ai" target="_blank" style="margin: 2px;">
|
||||
<img alt="ModelScope"
|
||||
src="https://img.shields.io/badge/ModelScope-Twinkle%20AI-4b6cb7?style=for-the-badge"
|
||||
style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
|
||||
<!-- Gemma 模型在 Hugging Face 上為 gated，使用者需同意 Google usage license -->
|
||||
<a href="https://huggingface.co/google/gemma-3-4b-pt" style="margin: 2px;">
|
||||
<img alt="License"
|
||||
src="https://img.shields.io/badge/License-Gemma-0081fb?style=for-the-badge"
|
||||
style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
|
||||
<a href="https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it/blob/main/README_EN.md" target="_blank" style="margin: 2px;">
|
||||
<img alt="English README"
|
||||
src="https://img.shields.io/badge/README-English-blue?style=for-the-badge&logo=google-translate&logoColor=white"
|
||||
style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
**gemma-3-4B-T1-it** 是專為中華民國台灣語境打造的繁體中文指令微調模型。本模型建構於 [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt) 架構之上，深度融合台灣人文社會脈絡與在地文化用語，能靈活應對法律條文釋義、學術教材編撰以及日常情境對話等多元任務。
|
||||
|
||||
此外，本模型在 **函式呼叫（Function Calling）** 結構理解與輸出穩定性 上進行了加強，為建構 AI Agent 或工具導向應用提供了良好的基礎能力。但模型本身不預設特定任務流程，適合搭配應用層的工具定義與控制邏輯，逐步發展符合實際需求的 Agent 系統。
|
||||
|
||||
> ⚠️ 規格重點：
|
||||
> 本模型為 純文本單模態（Single Modality）版本。
|
||||
|
||||
## Model Details
|
||||
|
||||
繼 [Formosa-1 Series](https://huggingface.co/collections/twinkle-ai/formosa-1-series) 在繁體中文開源社群獲得廣泛迴響後，Twinkle AI 持續致力於解決「模型中文化不足」與「語境文化隔閡」的痛點。gemma-3-4B-T1-it 是團隊在 Google Gemma 3 架構上的全新嘗試。有別於僅做語言翻譯的模型，T1 系列更加強調 **「台灣在地的人文社會底蘊」**。我們深知，語言是文化的載體，一個好的繁中模型不應只會寫繁體字，更要懂台灣的歷史脈絡、社會規範與法律體系。
|
||||
|
||||
> **T1**，是 **Taiwan** 的諧音縮寫，代表我們對於台灣本土文化的尊重與熱愛。
|
||||
|
||||
**核心特點 (Key Features)**
|
||||
1. **深度在地化與人文社會脈絡 (Cultural Alignment)：**
|
||||
* 針對台灣特有的 **人文社會學科（Humanities & Social Sciences）** 資料進行強化訓練。
|
||||
* 修正了常見的大型語言模型在台灣用語上的偏差（例如法律用語、政府機關稱謂、地名與歷史事件描述），使其生成的內容更符合台灣讀者的認知習慣。
|
||||
2. **Agent Base：強化的 Function Calling 能力：**
|
||||
* 訓練階段中，我們特別針對 **Function Calling 格式**進行強化，使模型具備良好的結構理解能力與工具調用潛力。
|
||||
* 模型能夠準確識別何時需要呼叫外部工具（API）、準確提取參數，並根據工具回傳的結果生成最終回覆。使用者可依自身應用場景（如 RAG、企業內部系統、自動化流程、專業決策支援等），進一步透過 **領域資料、工具定義與流程設計** 對模型進行強化與整合。
|
||||
3. **多元場景專精 (Multi-domain Expertise)：**
|
||||
* **法律實務：** 理解台灣法律條文結構，能協助進行基礎的條文釋義與法律文書輔助（註：僅供輔助，非正式法律意見）。
|
||||
* **教育輔助：** 適合用於編寫符合台灣課綱風格的教材、考題解析及教學大綱。
|
||||
* **生活應用：** 具備高指令跟隨能力（Instruction Following），無論是創意寫作、日常閒聊或資訊整理，都能提供精確且自然的繁體中文回應。
|
||||
|
||||
### Model Description
|
||||
|
||||
- **Developed by:** [Liang Hsun Huang](https://huggingface.co/lianghsun)、[Min Yi Chen](https://huggingface.co/minyichen)、[Wen Bin Lin](https://huggingface.co/tedslin) & [Dave Sung](https://huggingface.co/k1dave6412) (All authors have contributed equally to this work.)
|
||||
- **Funded by:** [APMIC](https://www.apmic.ai/), [Jerry Wu](https://huggingface.co/JerryWu)
|
||||
- **Base model:** [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt)
|
||||
- **Model type:** Gemma3ForConditionalGeneration (Transformers)
|
||||
- **Language(s) (NLP):** Traditional Chinese & English
|
||||
- **License:** gemma (Google usage license; gated on Hugging Face)
|
||||
|
||||
### Model Sources
|
||||
|
||||
- **Repository:** [twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it)
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Results
|
||||
|
||||
下表採用 [🌟 Twinkle Eval](https://github.com/ai-twinkle/Eval) 評測框架
|
||||
|
||||
|
||||
| 模型 | 評測模式 | TMMLU+(%) | 台灣法律(%) | MMLU(%) | 測試次數 | 選項排序 |
|
||||
|------------------------------------|:---------:|:----------------:|:----------------:|:----------------:|:---------:|:---------:|
|
||||
| [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) | box | 35.12 (±0.018) | 32.69 (±0.021) | 41.03 (±0.019) | 3 | 隨機 |
|
||||
| 🌟[twinkle-ai/Llama-3.2-3B-F1-Instruct](https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct) (ours) | box | 44.11 (±0.018) | 35.24 (±0.012) | 50.64 (±0.019) | 3 | 隨機 |
|
||||
| 🌟[twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it) (ours) | box | 47.44 (±0.018)| 44.18 (±0.022) | 59.13 (±0.021)| 3 | 隨機 |
|
||||
|
||||
### Function Calling Benchmark
|
||||
|
||||
我們採用了 **BFCL (Berkeley Function Calling Leaderboard)** 來評估模型在 Function Calling（函式呼叫）任務中的表現。
|
||||
|
||||
測試使用的指標如下：
|
||||
|
||||
- **AST Accuracy（AST 正確率）**：
|
||||
比較模型生成的函式呼叫與目標答案在抽象語法樹（AST）上的結構相似度。涵蓋四種題型：
|
||||
- 單一函式（Simple Function）
|
||||
- 多函式（Multiple Function）
|
||||
- 平行函式（Parallel Function）
|
||||
- 平行多函式（Parallel Multiple Function）
|
||||
|
||||
| Model | Overall Accuracy | AST Accuracy (S.) | AST Accuracy (M.) | AST Accuracy (P.) | AST Accuracy (P.M.) |
|
||||
|-----------------|------------------|-------------------|-------------------|-------------------|---------------------|
|
||||
| [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) | 61 | 64 | 88 | 56 | 36 |
|
||||
| 🌟[twinkle-ai/Llama-3.2-3B-F1-Instruct](https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct) (ours) | **91** | 93 | 95 | 91 | 87 |
|
||||
| 🌟[twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it) (ours) | 84.5 | 88 | 89 | 80 | 81 |
|
||||
|
||||
---
|
||||
## Model Responses
|
||||
|
||||
下列範例展示 **gemma-3-4B-it**(原版) 與 🌟**gemma-3-4B-T1-it**(ours) 在台灣語境任務中的差異。
|
||||
> 註：圖片中 👈 為 gemma-3-4B-it ； 👉 為 🌟gemma-3-4B-T1-it
|
||||
|
||||
### 地理位置
|
||||
|
||||
|
||||
|
||||
|
||||
### 本土用語
|
||||
|
||||
|
||||
|
||||
### 本土翻譯
|
||||
> 國外的模型翻譯幾乎都是「中國用語」
|
||||
|
||||
|
||||
|
||||
|
||||
### 台灣之光
|
||||
|
||||
|
||||
|
||||
### 台灣迷因
|
||||
|
||||
|
||||
|
||||
## 🔧 Tool Calling
|
||||
|
||||
本模型使用 Hermes 格式訓練，並支援平行呼叫（Parallel calling），以下為完整範例流程。
|
||||
Tool calling 模板已經為放置 chat_template。
|
||||
|
||||
### 1️⃣ 啟動 vLLM 後端
|
||||
|
||||
```bash
|
||||
vllm serve twinkle-ai/gemma-3-4B-T1-it \
|
||||
--port 8000 \
|
||||
--enable-auto-tool-choice \
|
||||
--tool-call-parser hermes
|
||||
```
|
||||
|
||||
### 2️⃣ 定義工具（Functions）
|
||||
|
||||
```python
|
||||
def get_weather(location: str, unit: str):
|
||||
return f"{location}的氣溫是{unit}26度，晴朗無風"
|
||||
|
||||
def search(query: str):
|
||||
return "川普終於宣布對等關稅政策，針對 18 個經濟體課徵一半的對等關稅，並從 4/5 起對所有進口產品徵收10%的基準關稅！美國將針對被認定為不當貿易行為(不公平貿易) 的國家，於 4/9 起課徵報復型對等關稅 (Discounted Reciprocal Tariff)，例如：日本將被課徵 24% 的關稅，歐盟則為 20%，以取代普遍性的 10% 關稅。\n針對中國則開啟新一波 34% 關稅，並疊加於先前已實施的關稅上，這將使中國進口商品的基本關稅稅率達到 54%，而且這尚未包含拜登總統任內或川普第一任期所施加的額外關稅。加拿大與墨西哥則不適用這套對等關稅制度，但川普認為這些國家在芬太尼危機與非法移民問題尚未完全解決，因此計畫對這兩國的大多數進口商品施加 25% 關稅。另外原本針對汽車與多數其他商品的關稅豁免將於 4/2 到期。\n台灣的部分，美國擬向台灣課徵32％的對等關稅，雖然並未針對晶片特別課徵關稅，但仍在記者會中提到台灣搶奪所有的電腦與半導體晶片，最終促成台積電對美國投資計劃額外加碼 1,000 億美元的歷史性投資；歐盟則課徵20％的對等關稅。最後是汽車關稅將於 4/2 起，對所有外國製造的汽車課徵25% 關稅。"
|
||||
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_weather",
|
||||
"description": "Get the current weather in a given location",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"location": {"type": "string", "description": "國家或城市名, e.g., 'Taipei'、'Jaipei'"},
|
||||
"unit": {"type": "string", "description": "氣溫單位，亞洲城市使用攝氏；歐美城市使用華氏", "enum": ["celsius", "fahrenheit"]}
|
||||
},
|
||||
"required": ["location", "unit"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "search",
|
||||
"description": "這是一個類似 Google 的搜尋引擎，關於知識、天氣、股票、電影、小說、百科等等問題，如果你不確定答案就搜尋一下。",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"query": {"type": "string", "description": "should be a search query, e.g., '2024 南韓 戒嚴'"}
|
||||
},
|
||||
"required": ["query"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
### 3️⃣ 執行工具調用（Tool Calls）
|
||||
|
||||
> **⚠️ 注意：system_prompt 可以不用帶，除非是需要時間基準的工具。**
|
||||
```python
|
||||
response = client.chat.completions.create(
|
||||
model=client.models.list().data[0].id,
|
||||
messages=[
|
||||
{"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
|
||||
{"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
|
||||
],
|
||||
max_tokens=1500,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
tools=tools,
|
||||
tool_choice="auto"
|
||||
)
|
||||
|
||||
print(response.choices[0].message.tool_calls)
|
||||
```
|
||||
|
||||
#### ⚙️ Tool Calls List:
|
||||
|
||||
|
||||
```json
|
||||
[ChatCompletionMessageToolCall(id='chatcmpl-tool-35e74420119349999913a10133b84bd3', function=Function(arguments='{"location": "Taipei", "unit": "celsius"}', name='get_weather'), type='function'), ChatCompletionMessageToolCall(id='chatcmpl-tool-7ffdcb98e59f4134a6171defe7f2e31b', function=Function(arguments='{"query": "Donald Trump latest tariffs policy"}', name='search'), type='function')]
|
||||
```
|
||||
|
||||
### 4️⃣ 產生最終回答
|
||||
|
||||
```python
|
||||
response = client.chat.completions.create(
|
||||
model=client.models.list().data[0].id,
|
||||
messages=[
|
||||
{"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
|
||||
{"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": response.choices[0].message.tool_calls[0].id,
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": response.choices[0].message.tool_calls[0].function.name,
|
||||
"arguments": response.choices[0].message.tool_calls[0].function.arguments
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": response.choices[0].message.tool_calls[1].id,
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": response.choices[0].message.tool_calls[1].function.name,
|
||||
"arguments": response.choices[0].message.tool_calls[1].function.arguments
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"content": search(**json.loads(response.choices[0].message.tool_calls[0].function.arguments)),
|
||||
"tool_call_id": response.choices[0].message.tool_calls[0].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"content": get_weather(**json.loads(response.choices[0].message.tool_calls[1].function.arguments)),
|
||||
"tool_call_id": response.choices[0].message.tool_calls[1].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
|
||||
}
|
||||
],
|
||||
max_tokens=1500,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
tools=tools,
|
||||
tool_choice="auto"
|
||||
)
|
||||
|
||||
print(response.choices[0].message.content)
|
||||
```
|
||||
|
||||
#### 📋 最終輸出內容：
|
||||
|
||||
```text
|
||||
以下是您請求的資訊：
|
||||
|
||||
**臺北市氣溫**
|
||||
- 目前的氣溫為 **26°C**（攝氏）
|
||||
- 天候狀況：晴朗無風
|
||||
|
||||
**川普最新關稅政策概述**
|
||||
1. **對等關稅政策**
|
||||
- 對 18 個經濟體課徵 50% 的對等關稅
|
||||
- 自 4 月 5 日起，所有進口產品全面徵收 10% 基本關稅
|
||||
|
||||
2. **報復型對等關稅**
|
||||
- 日本 24%、歐盟 20%
|
||||
|
||||
3. **對中國的高額關稅**
|
||||
- 增加至 54%（原有關稅 + 新增 34%）
|
||||
|
||||
4. **特殊案例**
|
||||
- 加拿大與墨西哥不適用，但其他商品課徵 25%
|
||||
- 汽車與部分商品的免稅即將到期
|
||||
|
||||
5. **對台灣的影響**
|
||||
- 美國計畫對台灣課徵 32% 關稅，但晶片暫無額外課稅
|
||||
|
||||
6. **全球視角**
|
||||
- 歐盟與日本關稅比例相對較高
|
||||
```
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
```yaml
|
||||
@misc{twinkleai2025gemma3t1,
|
||||
title = {gemma-3-4B-T1-it: A Traditional Chinese Instruction-Tuned Language Model for Taiwan},
|
||||
author = {Huang, Liang Hsun and Chen, Min Yi and Lin, Wen Bin and Sung, Dave},
|
||||
year = {2025},
|
||||
howpublished = {\url{https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it}},
|
||||
note = {Twinkle AI and APMIC. All authors contributed equally.}
|
||||
}
|
||||
```
|
||||
|
||||
## Acknowledge
|
||||
- 特此感謝 [APMIC](https://www.apmic.ai/) 的算力支援，才得以讓本專案訓利完成。
|
||||
- 特此致謝 [中央社](https://www.cna.com.tw/) 以及所有提供寶貴協助的夥伴。
|
||||
|
||||
## Model Card Authors
|
||||
|
||||
[Twinkle AI](https://huggingface.co/twinkle-ai)
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[Twinkle AI](https://huggingface.co/twinkle-ai)
|
||||
374
README_EN.md
Normal file
374
README_EN.md
Normal file
@@ -0,0 +1,374 @@
|
||||
---
|
||||
license: gemma
|
||||
language:
|
||||
- en
|
||||
- zh
|
||||
base_model:
|
||||
- google/gemma-3-4b-pt
|
||||
library_name: transformers
|
||||
tags:
|
||||
- Taiwan
|
||||
- R.O.C
|
||||
- zhtw
|
||||
- SLM
|
||||
- Gemma-3
|
||||
- gemma3
|
||||
datasets:
|
||||
- lianghsun/tw-reasoning-instruct
|
||||
- lianghsun/tw-contract-review-chat
|
||||
- minyichen/tw-instruct-R1-200k
|
||||
- minyichen/tw_mm_R1
|
||||
- minyichen/LongPaper_multitask_zh_tw_R1
|
||||
- nvidia/Nemotron-Instruction-Following-Chat-v1
|
||||
|
||||
model-index:
|
||||
- name: gemma-3-4B-T1-it
|
||||
results:
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: ikala/tmmluplus
|
||||
name: tmmlu+
|
||||
config: all
|
||||
split: test
|
||||
revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 47.44
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: cais/mmlu
|
||||
name: mmlu
|
||||
config: all
|
||||
split: test
|
||||
revision: c30699e
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 59.13
|
||||
- task:
|
||||
type: question-answering
|
||||
name: Single Choice Question
|
||||
dataset:
|
||||
type: lianghsun/tw-legal-benchmark-v1
|
||||
name: tw-legal-benchmark-v1
|
||||
config: all
|
||||
split: test
|
||||
revision: 66c3a5f
|
||||
metrics:
|
||||
- name: single choice
|
||||
type: accuracy
|
||||
value: 44.18
|
||||
metrics:
|
||||
- accuracy
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Model Card for gemma-3-4B-T1-it
|
||||
|
||||
<div align="center" style="line-height: 1;">
|
||||
<a href="https://discord.gg/Cx737yw4ed" target="_blank" style="margin: 2px;">
|
||||
<img alt="Discord" src="https://img.shields.io/badge/Discord-Twinkle%20AI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://huggingface.co/twinkle-ai" target="_blank" style="margin: 2px;">
|
||||
<img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Twinkle%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<!-- Gemma 模型在 Hugging Face 上為 gated，使用者需同意 Google usage license -->
|
||||
<a href="https://huggingface.co/google/gemma-3-4b-pt" style="margin: 2px;">
|
||||
<img alt="License" src="https://img.shields.io/badge/License-gemma-f5de53?&color=0081fb" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
<a href="https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it/blob/main/README.md" target="_blank" style="margin: 2px;">
|
||||
<img alt="繁體中文" src="https://img.shields.io/badge/README-繁體中文-4E9A06?logo=google-translate&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
|
||||
</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
<!-- Provide a quick summary of what the model is/does. -->
|
||||
**gemma-3-4B-T1-it** is a Traditional Chinese instruction-tuned model specifically designed for the context of Taiwan (Republic of China). Built upon the [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt) architecture, this model deeply integrates Taiwan's humanities, social context, and local terminology. It is capable of flexibly handling diverse tasks such as legal provision interpretation, academic material compilation, and daily situational dialogue.
|
||||
|
||||
Furthermore, this model has been strengthened in **Function Calling** structure understanding and output stability, providing a solid foundation for building AI Agents or tool-oriented applications. The model itself does not presuppose specific task workflows, making it suitable for integration with application-layer tool definitions and control logic to progressively develop Agent systems that meet practical needs.
|
||||
|
||||
⚠️ **Key Specification:** This model is a **Single Modality** version (text-only).
|
||||
|
||||
## Model Details
|
||||
|
||||
Following the widespread resonance of the [Formosa-1 Series](https://huggingface.co/collections/twinkle-ai/formosa-1-series) in the Traditional Chinese open-source community, Twinkle AI continues to dedicate itself to solving the pain points of "insufficient model localization" and "cultural context gaps." `gemma-3-4B-T1-Instruct` is the team's brand-new attempt based on the Google Gemma 3 architecture. Unlike models that merely perform language translation, the T1 Series places greater emphasis on "Taiwan's local humanities and social depth." We understand that language is a carrier of culture; a good Traditional Chinese model should not only know how to write Traditional Chinese characters but also understand Taiwan's historical context, social norms, and legal system.
|
||||
|
||||
### Key Features
|
||||
* **Cultural Alignment (Deep Localization & Humanities/Social Context):**
|
||||
* Enhanced training on data specific to Taiwan's **Humanities & Social Sciences.**
|
||||
* Corrected common biases in Large Language Models regarding Taiwanese terminology (e.g., legal terms, government agency titles, place names, and descriptions of historical events), ensuring generated content aligns with the cognitive habits of Taiwanese readers.
|
||||
|
||||
* **Agent Base: Enhanced Function Calling Capabilities:**
|
||||
* During the training phase, we specifically reinforced the **Function Calling** format, equipping the model with excellent structural understanding and tool invocation potential.
|
||||
* The model can accurately identify when to call external tools (APIs), precisely extract parameters, and generate final responses based on tool results. Users can further reinforce and integrate the model with domain data, tool definitions, and workflow designs according to their application scenarios (such as RAG, internal enterprise systems, automated processes, professional decision support, etc.).
|
||||
* **Multi-domain Expertise:**
|
||||
* **Legal Practice:** Understands the structure of Taiwan's legal provisions and can assist in basic provision interpretation and legal document support (Note: For assistance only; not formal legal advice).
|
||||
* **Education Support:** Suitable for compiling teaching materials, exam question analyses, and syllabuses that align with Taiwan's curriculum style.
|
||||
* **Life Applications:** Possesses high **Instruction Following** capabilities, providing precise and natural Traditional Chinese responses for creative writing, daily chat, or information organization.
|
||||
|
||||
### Model Description
|
||||
|
||||
- **Developed by:** [Liang Hsun Huang](https://huggingface.co/lianghsun)、[Min Yi Chen](https://huggingface.co/minyichen)、[Wen Bin Lin](https://huggingface.co/tedslin) & [Dave Sung](https://huggingface.co/k1dave6412) (All authors have contributed equally to this work.)
|
||||
- **Funded by:** [APMIC](https://www.apmic.ai/) & [Jerry Wu](https://huggingface.co/JerryWu)
|
||||
- **Base model:** [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt)
|
||||
- **Model type:** Gemma3ForConditionalGeneration (Transformers)
|
||||
- **Language(s) (NLP):** Traditional Chinese & English
|
||||
- **License:** gemma (Google usage license; gated on Hugging Face)
|
||||
|
||||
### Model Sources
|
||||
|
||||
- **Repository:** [twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it)
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Results
|
||||
|
||||
The table below uses the [🌟 Twinkle Eval](https://github.com/ai-twinkle/Eval) benchmark framework.
|
||||
|
||||
|
||||
| Model | Evaluation Mode | TMMLU+(%) | Taiwan Legal (%) | MMLU(%) | Runs | Option Ordering |
|
||||
|------------------------------------|:---------:|:----------------:|:----------------:|:----------------:|:---------:|:---------:|
|
||||
| [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) | box | 35.12 (±0.018) | 32.69 (±0.021) | 41.03 (±0.019) | 3 | Random |
|
||||
| 🌟[twinkle-ai/Llama-3.2-3B-F1-Instruct](https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct) (ours) | box | 44.11 (±0.018) | 35.24 (±0.012) | 50.64 (±0.019) | 3 | Random |
|
||||
| 🌟[twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it) (ours) | box | 47.44 (±0.018)| 44.18 (±0.022) | 59.13 (±0.021)| 3 | Random |
|
||||
|
||||
### Function Calling Benchmark
|
||||
|
||||
We utilized the **BFCL (Berkeley Function Calling Leaderboard)** to evaluate the model's performance in Function Calling tasks.
|
||||
|
||||
The metrics used are as follows:
|
||||
* AST Accuracy: Compares the structural similarity between the model-generated function call and the target answer on the Abstract Syntax Tree (AST).
|
||||
* It covers four types of questions:
|
||||
* Simple Function
|
||||
* Multiple Function
|
||||
* Parallel Function
|
||||
* Parallel Multiple Function
|
||||
|
||||
| Model | Overall Accuracy | AST Accuracy (S.) | AST Accuracy (M.) | AST Accuracy (P.) | AST Accuracy (P.M.) |
|
||||
|-----------------|------------------|-------------------|-------------------|-------------------|---------------------|
|
||||
| [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it) | 61 | 64 | 88 | 56 | 36 |
|
||||
| 🌟[twinkle-ai/Llama-3.2-3B-F1-Instruct](https://huggingface.co/twinkle-ai/Llama-3.2-3B-F1-Instruct) (ours) | **91** | 93 | 95 | 91 | 87 |
|
||||
| 🌟[twinkle-ai/gemma-3-4B-T1-it](https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it) (ours) | 84.5 | 88 | 89 | 80 | 81 |
|
||||
|
||||
---
|
||||
## Model Responses
|
||||
|
||||
The following examples demonstrate the differences between **gemma-3-4B-it (Original)** and **🌟 gemma-3-4B-T1-it (Ours)** in Taiwan-specific contexts.
|
||||
> Note: In the image, 👈 denotes gemma-3-4B-it; 👉 denotes 🌟gemma-3-4B-T1-it.
|
||||
|
||||
### Geographical Knowledge
|
||||
|
||||
|
||||
|
||||
### Taiwanese Slang
|
||||
|
||||
|
||||
|
||||
### Localized Translation
|
||||
> Translations generated by foreign models almost exclusively use Mainland Chinese terminology.
|
||||
|
||||
|
||||
|
||||
### The Pride of Taiwan
|
||||
|
||||
|
||||
|
||||
### Taiwanese Memes
|
||||
|
||||
|
||||
|
||||
## 🔧 Tool Calling
|
||||
|
||||
This model is trained using the **Hermes** format and supports **Parallel calling**. Below is a complete example workflow. The Tool calling template is already integrated into the `chat_template`.
|
||||
|
||||
### 1️⃣ Start vLLM Backend
|
||||
|
||||
```bash
|
||||
vllm serve twinkle-ai/gemma-3-4B-T1-it \
|
||||
--port 8000 \
|
||||
--enable-auto-tool-choice \
|
||||
--tool-call-parser hermes
|
||||
```
|
||||
|
||||
### 2️⃣ Define Tools (Functions)
|
||||
|
||||
```python
|
||||
def get_weather(location: str, unit: str):
|
||||
return f"{location}的氣溫是{unit}26度，晴朗無風"
|
||||
|
||||
def search(query: str):
|
||||
return "川普終於宣布對等關稅政策，針對 18 個經濟體課徵一半的對等關稅，並從 4/5 起對所有進口產品徵收10%的基準關稅！美國將針對被認定為不當貿易行為(不公平貿易) 的國家，於 4/9 起課徵報復型對等關稅 (Discounted Reciprocal Tariff)，例如：日本將被課徵 24% 的關稅，歐盟則為 20%，以取代普遍性的 10% 關稅。\n針對中國則開啟新一波 34% 關稅，並疊加於先前已實施的關稅上，這將使中國進口商品的基本關稅稅率達到 54%，而且這尚未包含拜登總統任內或川普第一任期所施加的額外關稅。加拿大與墨西哥則不適用這套對等關稅制度，但川普認為這些國家在芬太尼危機與非法移民問題尚未完全解決，因此計畫對這兩國的大多數進口商品施加 25% 關稅。另外原本針對汽車與多數其他商品的關稅豁免將於 4/2 到期。\n台灣的部分，美國擬向台灣課徵32％的對等關稅，雖然並未針對晶片特別課徵關稅，但仍在記者會中提到台灣搶奪所有的電腦與半導體晶片，最終促成台積電對美國投資計劃額外加碼 1,000 億美元的歷史性投資；歐盟則課徵20％的對等關稅。最後是汽車關稅將於 4/2 起，對所有外國製造的汽車課徵25% 關稅。"
|
||||
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_weather",
|
||||
"description": "Get the current weather in a given location",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"location": {"type": "string", "description": "國家或城市名, e.g., 'Taipei'、'Jaipei'"},
|
||||
"unit": {"type": "string", "description": "氣溫單位，亞洲城市使用攝氏；歐美城市使用華氏", "enum": ["celsius", "fahrenheit"]}
|
||||
},
|
||||
"required": ["location", "unit"]
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "search",
|
||||
"description": "這是一個類似 Google 的搜尋引擎，關於知識、天氣、股票、電影、小說、百科等等問題，如果你不確定答案就搜尋一下。",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"query": {"type": "string", "description": "should be a search query, e.g., '2024 南韓 戒嚴'"}
|
||||
},
|
||||
"required": ["query"]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
### 3️⃣ Execute Tool Calls
|
||||
|
||||
> **⚠️ Note: `system_prompt` is optional unless the tool requires a time reference.**
|
||||
```python
|
||||
response = client.chat.completions.create(
|
||||
model=client.models.list().data[0].id,
|
||||
messages=[
|
||||
{"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
|
||||
{"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
|
||||
],
|
||||
max_tokens=1500,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
tools=tools,
|
||||
tool_choice="auto"
|
||||
)
|
||||
|
||||
print(response.choices[0].message.tool_calls)
|
||||
```
|
||||
|
||||
#### ⚙️ Tool Calls List:
|
||||
|
||||
|
||||
```json
|
||||
[ChatCompletionMessageToolCall(id='chatcmpl-tool-35e74420119349999913a10133b84bd3', function=Function(arguments='{"location": "Taipei", "unit": "celsius"}', name='get_weather'), type='function'), ChatCompletionMessageToolCall(id='chatcmpl-tool-7ffdcb98e59f4134a6171defe7f2e31b', function=Function(arguments='{"query": "Donald Trump latest tariffs policy"}', name='search'), type='function')]
|
||||
```
|
||||
|
||||
### 4️⃣ Generate Final Answer
|
||||
|
||||
```python
|
||||
response = client.chat.completions.create(
|
||||
model=client.models.list().data[0].id,
|
||||
messages=[
|
||||
{"role": "system", "content": "記住你的知識截止於 2024/12，今天是 2025/4/7"},
|
||||
{"role": "user", "content": "台北氣溫如何? 另外，告訴我川普最新關稅政策"},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": response.choices[0].message.tool_calls[0].id,
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": response.choices[0].message.tool_calls[0].function.name,
|
||||
"arguments": response.choices[0].message.tool_calls[0].function.arguments
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": response.choices[0].message.tool_calls[1].id,
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": response.choices[0].message.tool_calls[1].function.name,
|
||||
"arguments": response.choices[0].message.tool_calls[1].function.arguments
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"content": search(**json.loads(response.choices[0].message.tool_calls[0].function.arguments)),
|
||||
"tool_call_id": response.choices[0].message.tool_calls[0].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"content": get_weather(**json.loads(response.choices[0].message.tool_calls[1].function.arguments)),
|
||||
"tool_call_id": response.choices[0].message.tool_calls[1].id # tool_call_id 必須要帶，才能正確配對 工具 及 tool_call
|
||||
}
|
||||
],
|
||||
max_tokens=1500,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
tools=tools,
|
||||
tool_choice="auto"
|
||||
)
|
||||
|
||||
print(response.choices[0].message.content)
|
||||
```
|
||||
|
||||
#### 📋 Final Output Content:
|
||||
|
||||
```text
|
||||
以下是您請求的資訊：
|
||||
|
||||
**臺北市氣溫**
|
||||
- 目前的氣溫為 **26°C**（攝氏）
|
||||
- 天候狀況：晴朗無風
|
||||
|
||||
**川普最新關稅政策概述**
|
||||
1. **對等關稅政策**
|
||||
- 對 18 個經濟體課徵 50% 的對等關稅
|
||||
- 自 4 月 5 日起，所有進口產品全面徵收 10% 基本關稅
|
||||
|
||||
2. **報復型對等關稅**
|
||||
- 日本 24%、歐盟 20%
|
||||
|
||||
3. **對中國的高額關稅**
|
||||
- 增加至 54%（原有關稅 + 新增 34%）
|
||||
|
||||
4. **特殊案例**
|
||||
- 加拿大與墨西哥不適用，但其他商品課徵 25%
|
||||
- 汽車與部分商品的免稅即將到期
|
||||
|
||||
5. **對台灣的影響**
|
||||
- 美國計畫對台灣課徵 32% 關稅，但晶片暫無額外課稅
|
||||
|
||||
6. **全球視角**
|
||||
- 歐盟與日本關稅比例相對較高
|
||||
```
|
||||
|
||||
|
||||
## Citation
|
||||
|
||||
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
||||
```yaml
|
||||
@misc{twinkleai2025gemma3t1,
|
||||
title = {gemma-3-4B-T1-it: A Traditional Chinese Instruction-Tuned Language Model for Taiwan},
|
||||
author = {Huang, Liang Hsun and Chen, Min Yi and Lin, Wen Bin and Sung, Dave},
|
||||
year = {2025},
|
||||
howpublished = {\url{https://huggingface.co/twinkle-ai/gemma-3-4B-T1-it}},
|
||||
note = {Twinkle AI and APMIC. All authors contributed equally.}
|
||||
}
|
||||
```
|
||||
|
||||
## Acknowledge
|
||||
We would like to express our gratitude to [APMIC](https://apmic.ai/) for providing computing power support, enabling the successful completion of this project training. Special thanks to [CNA](https://focustaiwan.tw/) and all partners who provided valuable assistance.
|
||||
|
||||
## Model Card Authors
|
||||
|
||||
[Twinkle AI](https://huggingface.co/twinkle-ai)
|
||||
|
||||
## Model Card Contact
|
||||
|
||||
[Twinkle AI](https://huggingface.co/twinkle-ai)
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
73
config.json
Normal file
73
config.json
Normal file
@@ -0,0 +1,73 @@
|
||||
{
|
||||
"_sliding_window_pattern": 6,
|
||||
"architectures": [
|
||||
"Gemma3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"attn_logit_softcapping": null,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"eos_token_id": 1,
|
||||
"final_logit_softcapping": null,
|
||||
"head_dim": 256,
|
||||
"hidden_activation": "gelu_pytorch_tanh",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 10240,
|
||||
"layer_types": [
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"full_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention",
|
||||
"sliding_attention"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "gemma3_text",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 34,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"query_pre_attn_scalar": 256,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_local_base_freq": 10000.0,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"rope_type": "linear"
|
||||
},
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 1024,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.55.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 262208
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.55.2"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c30cc953abc05d76ec8d62d3bb63bbd8467de0807d005e284f3e02b3548f16a
|
||||
size 4960531344
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0534dfc46cd45f37f642788206f364bc31106e024e58705dd45e92869eb9af3d
|
||||
size 4142551864
|
||||
453
model.safetensors.index.json
Normal file
453
model.safetensors.index.json
Normal file
@@ -0,0 +1,453 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3880263168,
|
||||
"total_size": 9103031296
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": {
|
||||
"content": "<end_of_turn>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"image_token": "<image_soft_token>",
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
3
tokenizer_config.json
Normal file
3
tokenizer_config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:227c6f91376cb7b90efe1940518366797ae053737f96c2d67e30afedd4b09084
|
||||
size 1159886
|
||||
Reference in New Issue
Block a user