基础模型:
- mlabonne/AlphaMonarch-7B
- datatab/Yugo55-GPT-v4
- datatab/Yugo55-GPT-DPO-v1-chkp-300
- NousResearch/Nous-Hermes-2-Mistral-7B-DPO
库名称: transformers
标签:
- mergekit
- merge
- 文本生成推理
- transformers
- mistral
许可证: mit
语言:
- 塞尔维亚语
数据集:
- datatab/alpaca-cleaned-serbian-full
- datatab/ultrafeedback_binarized
- datatab/open-orca-slim-serbian
Yugo55A-GPT 4bit
🏆 评估结果
评估结果通过塞尔维亚LLM评估获得,由Aleksa Gordić发布: serbian-llm-eval
模型 |
ARC-E |
ARC-C |
Hellaswag |
BoolQ |
Winogrande |
OpenbookQA |
PiQA |
*Yugo55-GPT-v4-4bit |
51.41 |
36.00 |
57.51 |
80.92 |
65.75 |
34.70 |
70.54 |
Yugo55A-GPT |
51.52 |
37.78 |
57.52 |
84.40 |
65.43 |
35.60 |
69.43 |
🔗 合并详情
合并方法
这是使用mergekit合并预训练语言模型的结果。
该模型采用线性合并方法。
合并的模型
合并包含以下模型:
🧩 配置
生成此模型使用的YAML配置如下:
models:
- model: datatab/Yugo55-GPT-v4
parameters:
weight: 1.0
- model: datatab/Yugo55-GPT-DPO-v1-chkp-300
parameters:
weight: 1.0
- model: mlabonne/AlphaMonarch-7B
parameters:
weight: 0.5
- model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
parameters:
weight: 0.5
merge_method: linear
dtype: float16
💻 使用方式
!pip -q install git+https://github.com/huggingface/transformers # 需要从github安装
!pip install -q datasets loralib sentencepiece
!pip -q install bitsandbytes accelerate
from IPython.display import HTML, display
def set_css():
display(HTML('''
<style>
pre {
white-space: pre-wrap;
}
</style>
'''))
get_ipython().events.register('pre_run_cell', set_css)
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
"datatab/Yugo55A-GPT", torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained(
"datatab/Yugo55A-GPT", torch_dtype="auto"
)
from typing import Optional
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
def generate(
user_content: str, system_content: Optional[str] = ""
) -> str:
system_content = "以下是描述任务的指令,配以提供额外上下文的输入。请编写一个适当完成要求的回答。"
messages = [
{
"role": "system",
"content": system_content,
},
{"role": "user", "content": user_content},
]
tokenized_chat = tokenizer.apply_chat_template(
messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to("cuda")
text_streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
output = model.generate(
tokenized_chat,
streamer=text_streamer,
max_new_tokens=2048,
temperature=0.1,
repetition_penalty=1.11,
top_p=0.92,
top_k=1000,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
do_sample=True,
)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
generate("列举太阳系的所有行星并告诉我哪颗行星最大")
generate("美洲驼、骆马和羊驼有什么区别?")
generate("给Sam Altman写一封简短的电子邮件,说明开源GPT-4的理由")