ieit-yuan/yuan2.0-2b 🔢📝 → 📝
About
Yuan2.0 is a new generation LLM developed by IEIT System, enhanced the model's understanding of semantics, mathematics, reasoning, code, knowledge, and other aspects.
Example Output
Prompt:
"你是一个在中国菜肴方面的资深厨师,请你详细介绍下宫保鸡丁的做法?"
Output
宫保鸡丁是一道传统的中国菜肴,以鸡肉、花生和蔬菜为主要材料。下面是宫保鸡丁的做法:
材料:
- 鸡胸肉:250克
- 花生:适量
- 干辣椒:适量
- 葱姜蒜:适量
- 料酒:适量
- 生抽:适量
- 盐:适量
- 糖:适量
- 鸡精:适量
- 淀粉:适量
- 鸡蛋清:适量
- 食用油:适量
步骤:
- 将鸡胸肉切成小块,加入料酒、生抽、盐、糖、鸡精和淀粉,搅拌均匀腌制15分钟。
- 将花生炒熟备用。
- 锅中倒入适量的食用油,加入葱姜蒜炒香。
- 加入腌制好的鸡丁翻炒至变色。
- 加入适量的水,煮开后加入花生,继续翻炒均匀。
- 加入干辣椒炒香,再加入适量的盐、糖、鸡精调味。
- 用水淀粉勾芡,使汤汁变稠。
- 最后加入炒熟的花生,翻炒均匀即可。
宫保鸡丁的做法相对简单,但需要掌握火候和调味的比例。根据个人口味,可以适量调整辣椒的用量,增加或减少辣度。此外,也可以根据个人喜好添加其他蔬菜或调料,如胡萝卜丁、青椒等,增加口感和营养。
Performance Metrics
10.25s
Prediction Time
10.29s
Total Time
All Input Parameters
{
"top_k": 50,
"top_p": 1,
"prompt": "你是一个在中国菜肴方面的资深厨师,请你详细介绍下宫保鸡丁的做法?",
"temperature": 1,
"max_new_tokens": 1024
}
Input Parameters
- top_k
- The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering).
- top_p
- A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751).
- prompt (required)
- temperature
- The value used to modulate the next token probabilities.
- max_new_tokens
- The maximum number of tokens the model should generate as output.
Output Schema
Output
Version Details
- Version ID
4bf8b60f7222f534ea5891866c122f781d07edeaedf9cc2d8277e9e652c581a0- Version Created
- January 12, 2024