Qwen-7B-Chat-GGUF

์ด ์ €์žฅ์†Œ๋Š” Qwen/Qwen-7B-Chat ๋ชจ๋ธ์„ GGUF๋กœ ๋ณ€ํ™˜ํ•˜๊ณ  ์–‘์žํ™”ํ•œ ๊ฒฐ๊ณผ๋ฌผ์ž…๋‹ˆ๋‹ค.

์ƒ์„ฑ ์ •๋ณด

  • ์›๋ณธ ๋ชจ๋ธ: Qwen/Qwen-7B-Chat
  • ์›๋ณธ revision: main
  • ์ƒค๋“œ ๋ณ‘ํ•ฉ ์‚ฌ์šฉ: False
  • ๊ธฐ๋ณธ GGUF ํƒ€์ž…: f16
  • ์–‘์žํ™” ํƒ€์ž…: Q2_K, Q3_K, Q4_K, Q5_K, Q6_K, Q8_0

ํŒŒ์ผ ๋ชฉ๋ก

  • Qwen-7B-Chat-f16.gguf
  • Qwen-7B-Chat-Q2_K.gguf
  • Qwen-7B-Chat-Q3_K.gguf
  • Qwen-7B-Chat-Q4_K.gguf
  • Qwen-7B-Chat-Q5_K.gguf
  • Qwen-7B-Chat-Q6_K.gguf
  • Qwen-7B-Chat-Q8_0.gguf
  • quantizer-manifest.json

์‚ฌ์šฉ ์˜ˆ์‹œ

./llama-cli -m Qwen-7B-Chat-f16.gguf -p "์•ˆ๋…•ํ•˜์„ธ์š”"

์ฐธ๊ณ 

  • ๋ณ€ํ™˜/์–‘์žํ™”๋Š” llama.cpp ๋„๊ตฌ ์ฒด์ธ์„ ์‚ฌ์šฉํ–ˆ์Šต๋‹ˆ๋‹ค.
  • ์ƒ์„ฑ ๊ณผ์ • ๋ฉ”ํƒ€๋ฐ์ดํ„ฐ๋Š” quantizer-manifest.json ํŒŒ์ผ์— ํฌํ•จ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
Downloads last month
264
GGUF
Model size
8B params
Architecture
qwen
Hardware compatibility
Log In to add your hardware

2-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for h31337/Qwen-7B-Chat-GGUF

Quantized
(8)
this model