124 lines
3.2 KiB
Markdown
124 lines
3.2 KiB
Markdown
---
|
|
license: llama2
|
|
metrics:
|
|
- code_eval
|
|
library_name: transformers
|
|
tags:
|
|
- code
|
|
model-index:
|
|
- name: DataLinguistic-34B-V1.0
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
dataset:
|
|
type: openai_humaneval
|
|
name: HumanEval
|
|
metrics:
|
|
- name: pass@1
|
|
type: pass@1
|
|
value: 0.701
|
|
verified: false
|
|
|
|
|
|
---
|
|
|
|
# DataLinguistic-34B-V1.0 Chinese-English Question Answering Model
|
|
|
|
## Model Overview
|
|
|
|
DataLinguistic-34B-V1.0 is a Chinese-English question answering model fine-tuned from Huggingface's CodeLlama-34b model with 4-bit quantization on DataLinguistic's proprietary datasets.
|
|
|
|
## Model Architecture
|
|
|
|
DataLinguistic-34B-4bit-V1.0 inherits the encoder-decoder structure from Llama with 34B parameters.
|
|
|
|
## Training Datasets
|
|
|
|
The model was trained on the following open-source datasets:
|
|
|
|
- Data_OpenSet: Chinese-English question-answering dataset curated from junelee/wizard_vicuna_70k
|
|
- Data_OpenSet2: Chinese-English question-answering dataset curated from garage-bAInd/Open-Platypus
|
|
- Proprietary Chinese-English question-answering dataset collected internally by DataLinguistic (not open-sourced)
|
|
|
|
The data is formatted as:
|
|
""
|
|
|
|
|
|
\<s>please answer my question in datalynn model and Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: {question}\</s>
|
|
|
|
|
|
## Use Cases
|
|
|
|
The model can be used for a wide range of Chinese-English question answering and chatbot applications.
|
|
|
|
## Model Advantages
|
|
|
|
- Based on huge model CodeLlama-34b with 34B parameters
|
|
- Fine-tuned on large-scale Chinese-English QA datasets for high quality
|
|
|
|
## Usage
|
|
|
|
1. Install model from Huggingface
|
|
2. Import and initialize model
|
|
3. Input question, generate answer
|
|
|
|
## Version
|
|
|
|
Current version: DataLinguistic-34B-V1.0
|
|
|
|
## Author
|
|
|
|
Tang Zhengzheng
|
|
|
|
## Contributors
|
|
|
|
DataLinguistic team
|
|
|
|
# DataLinguistic-34B-V1.0 中英文问答模型
|
|
|
|
## 模型简介
|
|
|
|
DataLinguistic-34B-V1.0是一个基于Huggingface的CodeLlama-34b模型在DataLinguistic自建数据集上微调的中文英文问答模型。
|
|
|
|
## 模型结构
|
|
|
|
DataLinguistic-34B-V1.0 inherits the encoder-decoder structure from CodeLlama with 34B parameters.
|
|
|
|
## 模型训练数据集
|
|
|
|
模型使用了以下开源数据集进行了训练:
|
|
|
|
- Data_OpenSet: 基于junelee/wizard_vicuna_70k整理的中英文问答数据集
|
|
- Data_OpenSet2: 基于garage-bAInd/Open-Platypus整理的中英文问答数据集
|
|
- DataLinguistic内部收集的专属中英文问答数据集(未开源)
|
|
|
|
数据集采用如下格式:
|
|
|
|
\<s>please answer my question in datalynn model and Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: {question}\</s>
|
|
|
|
## 应用场景
|
|
|
|
该模型可广泛应用于中英文问答、聊天机器人等场景。
|
|
|
|
## 模型优势
|
|
|
|
- 基于大模型Llama-34b,参数量达34亿
|
|
- 在大规模中英文问答数据集上进行微调,质量较高
|
|
|
|
## 使用步骤
|
|
|
|
1. 在Huggingface安装模型
|
|
2. 导入并初始化模型
|
|
3. 输入问题,生成回答
|
|
|
|
## 版本信息
|
|
|
|
当前版本:DataLinguistic-34B-V1.0
|
|
|
|
## 作者
|
|
|
|
唐正正
|
|
|
|
## 贡献者
|
|
|
|
DataLinguistic团队 |