87 lines
3.4 KiB
Markdown
87 lines
3.4 KiB
Markdown
|
---
|
||
|
|
base_model:
|
||
|
|
- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
||
|
|
- taide/Llama-3.1-TAIDE-LX-8B-Chat
|
||
|
|
- meta-llama/Llama-3.1-8B-Instruct
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# voidful/Llama-3.1-TAIDE-R1-8B-Chat
|
||
|
|
|
||
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||
|
|
|
||
|
|
## Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
import vllm
|
||
|
|
from transformers import AutoTokenizer
|
||
|
|
from vllm import LLM, SamplingParams
|
||
|
|
|
||
|
|
model_name = "voidful/Llama-3.1-TAIDE-R1-8B-Chat"
|
||
|
|
llm = vllm.LLM(model=model_name,max_model_len=4096)
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||
|
|
|
||
|
|
messages = [
|
||
|
|
{"role": "user", "content": f"早餐喝早餐店的奶茶會導致烙賽為什麼?"},
|
||
|
|
]
|
||
|
|
prompts = tokenizer.apply_chat_template(
|
||
|
|
messages,
|
||
|
|
add_generation_prompt=True,
|
||
|
|
tokenize=False
|
||
|
|
)
|
||
|
|
|
||
|
|
sampling_params = SamplingParams(temperature=0.6, max_tokens=512, top_p=0.9)
|
||
|
|
outputs = llm.generate(prompts, sampling_params)
|
||
|
|
|
||
|
|
print(f"{prompts}")
|
||
|
|
print(f"{outputs[0].outputs[0].text}\n")
|
||
|
|
|
||
|
|
|
||
|
|
sampling_params = SamplingParams(temperature=0.6, max_tokens=512, top_p=0.9)
|
||
|
|
outputs = llm.generate(prompts, sampling_params)
|
||
|
|
|
||
|
|
print(f"{prompts}")
|
||
|
|
print(f"{outputs[0].outputs[0].text}\n")
|
||
|
|
```
|
||
|
|
|
||
|
|
Output
|
||
|
|
```
|
||
|
|
<think> 關於「早餐喝早餐店的奶茶會導致烙賽」的問題，可能的原因有幾種可能的解釋。首先，「烙賽」這個詞在台灣的網路用語中，通常指的是「燒腸」或「拉肚子」的意思，指的是人體的腸胃或腸道發生不舒服的狀況，可能是消化不良、腹泻、或其他腸胃道的問題。所以，喝了不健康的飲料，可能會導致腸胃不舒服，引起「烙賽」的反應。
|
||
|
|
|
||
|
|
其次，一個可能的原因是，早餐店的奶茶可能使用了低品質的奶源、含糖或含奶精等添加物。奶精是一種人工添加劑，可能會對胃造成刺激或不舒服的感覺。再者，早餐的奶茶可能是用即溶的粉末或濃縮的奶來泡的，這些東西可能含有許多添加劑或不健康的成分。
|
||
|
|
|
||
|
|
最後，個人的體質也是一個因素。有人可能對奶或糖有過敏或不耐受的反應，喝了之後就會出現不舒服的症狀。
|
||
|
|
|
||
|
|
綜合上述的原因，早餐喝早餐店的奶茶可能會導致烙賽的原因有：使用低品質的奶源、含糖或奶精等添加劑、個人的體質對奶或糖有過敏或不耐受的反應等。
|
||
|
|
|
||
|
|
<answer> 早餐喝早餐店的奶茶可能導致烙賽的原因有低品質的奶源、含糖或奶精等添加劑、以及個人的體質對奶或糖有過敏或不耐受的反應等。這是因為不健康的飲料成分可能會對身體造成不舒服的影響。</answer>
|
||
|
|
```
|
||
|
|
|
||
|
|
## Merge Details
|
||
|
|
### Merge Method
|
||
|
|
|
||
|
|
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)
|
||
|
|
* [taide/Llama-3.1-TAIDE-LX-8B-Chat](https://huggingface.co/taide/Llama-3.1-TAIDE-LX-8B-Chat)
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
merge_method: sce
|
||
|
|
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||
|
|
tokenizer:
|
||
|
|
source: taide/Llama-3.1-TAIDE-LX-8B-Chat
|
||
|
|
models:
|
||
|
|
- model: taide/Llama-3.1-TAIDE-LX-8B-Chat
|
||
|
|
- model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
||
|
|
```
|