ieit-yuan/yuan2.0-51b ๐Ÿ”ข๐Ÿ“ โ†’ ๐Ÿ“

โ–ถ๏ธ 42 runs ๐Ÿ“… Feb 2024 โš™๏ธ Cog 0.9.4 ๐Ÿ”— GitHub ๐Ÿ“„ Paper โš–๏ธ License
code-generation text-generation text-translation

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:

"่ฏทไป‹็ป็บข็ƒง่‚‰็š„ๅšๆณ•ใ€‚"

Output

็บข็ƒง่‚‰ๆ˜ฏไธ€้“ไผ ็ปŸ็š„ๅฎถๅธธ่œ๏ผŒๅœจไธญๅ›ฝๅ„ๅœฐ้ƒฝๆœ‰็€ๅนฟๆณ›็š„ๆต่กŒใ€‚ไปฅไธ‹ๆ˜ฏ็บข็ƒง่‚‰็š„ๅšๆณ•๏ผš
ๆ‰€้œ€ๆๆ–™๏ผš

  • ไบ”่Šฑ่‚‰ 250ๅ…‹
  • ่‘ฑๅงœ่’œ้€‚้‡
  • ่ฑ†็“ฃ้…ฑ้€‚้‡
  • ็”ŸๆŠฝ้€‚้‡
  • ่€ๆŠฝ้€‚้‡
  • ๆ–™้…’้€‚้‡
  • ็™ฝ็ณ–้€‚้‡
  • ็›้€‚้‡
    ๆญฅ้ชค๏ผš
  1. ๅฐ†ไบ”่Šฑ่‚‰ๅˆ‡ๆˆๅคงๅฐ้€‚ไธญ็š„ๅ—็Šถ๏ผŒๆ”พๅ…ฅๆธ…ๆฐดไธญ็„ฏๆฐด๏ผŒๆ”พๅ…ฅๆฐดไธญๆตธๆณก10ๅˆ†้’Ÿใ€‚
  2. ็ƒญ้”…ๅ‡‰ๆฒน๏ผŒๅฐ†่‘ฑๅงœ่’œๅˆ‡็ขŽๅค‡็”จใ€‚
  3. ๅฐ†็„ฏๆฐดๅŽ็š„ไบ”่Šฑ่‚‰ๅ—ๆ”พๅ…ฅ้”…ไธญ๏ผŒๅ€’ๅ…ฅๆ–™้…’๏ผŒ็…ธ็‚’่‡ณ่‚‰ๅ—่กจ้ขๅ‡ๅŒ€ใ€‚
  4. ๅŠ ๅ…ฅ้€‚้‡็š„็”ŸๆŠฝใ€่€ๆŠฝใ€็™ฝ็ณ–๏ผŒ็…ธ็‚’่‡ณ่‚‰ๅ—่กจ้ขๅ‡ๅŒ€ใ€‚
  5. ๅŠ ๅ…ฅ้€‚้‡็š„ๆฐด๏ผŒ็›–ไธŠ้”…็›–๏ผŒ็”จไธญๅฐ็ซๆ…ข็‚–15-20ๅˆ†้’Ÿๅทฆๅณ๏ผŒ็›ดๅˆฐ่‚‰ๅ—่กจ้ขๅ˜ๆˆ้‡‘้ป„่‰ฒใ€‚
  6. ๅฐ†็บข็ƒง่‚‰่ฃ…็›˜๏ผŒๆ’’ไธŠ่‘ฑ่Šฑ๏ผŒๅณๅฏ้ฃŸ็”จใ€‚
    ้œ€่ฆๆณจๆ„็š„ๆ˜ฏ๏ผŒ็บข็ƒง่‚‰็š„ๅฃๆ„Ÿๅ–ๅ†ณไบŽ็ซๅ€™ๅ’Œ่‰ๆ–™็ง็ฑป็š„ๆ‹ฉไผ˜ๅ’Œ่ฐƒๅ’Œ๏ผŒๅ’Œไธชไบบๅฃๅ‘ณๆœ‰ๅ…ณ๏ผŒๅปบ่ฎฎๅœจๅš่œไน‹ๅ‰๏ผŒๅ…ˆๅŽปๆŽŒๆก็บข็ƒง่‚‰็š„ๅฃๅ‘ณ็‰น็‚นใ€‚

Performance Metrics

105.70s Prediction Time
783.19s Total Time
All Input Parameters
{
  "top_k": 50,
  "top_p": 1,
  "prompt": "่ฏทไป‹็ป็บข็ƒง่‚‰็š„ๅšๆณ•ใ€‚",
  "temperature": 1,
  "max_new_tokens": 4096
}
Input Parameters
top_k Type: integerDefault: 50
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 Type: numberDefault: 1
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) Type: string
temperature Type: numberDefault: 1
The value used to modulate the next token probabilities.
max_new_tokens Type: integerDefault: 4096
The maximum number of tokens the model should generate as output.
Output Schema

Output

Type: string

Version Details
Version ID
28238b6df8047a775fc5fa65512d6ab5b649f98f8cb6eec8844c27214ec240cf
Version Created
February 9, 2024
Run on Replicate โ†’