Edit model card

42dot_LLM-PLM-1.3B_GGUF

์„ค๋ช…

42dot ๋ชจ๋ธ์˜ GGUF ๊ฒฝ๋Ÿ‰ํ™” ๋ชจ๋ธ์„ ๋งŒ๋“ค์–ด ๋’€์Šต๋‹ˆ๋‹ค.

42dot_LLM-PLM-1.3B

ํŒŒ์ผ

๋งํฌ์— ์—ฐ๊ฒฐ ํ•ด๋‘์—ˆ์œผ๋‹ˆ ํ•„์š”ํ•˜์‹  ๋ถ„์€ ํ•˜ํŠธ ์ฃผ๊ณ  ์ฑ™๊ฒจ ๊ฐ€์„ธ์š”. gguf ์›๋ณธ ํŒŒ์ผ

Q4, Q8 ๊ฒฝ๋Ÿ‰ํ™” ํŒŒ์ผ

์ด์™ธ ๋ชจ๋ธ์€ ๊ทผ๋ณธ ์—†์–ด์„œ ์˜ฌ๋ฆด๊นŒ ํ•˜๋‹ค๊ฐ€ ์•ˆ ์˜ฌ๋ฆฌ๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค.

์‚ฌ์šฉ๋ฒ•

์›๋ณธ

์›๋ณธ ๋งํฌ์—์„œ ์‚ฌ์šฉ ๋ฒ•์„ ํ™•์ธํ•˜์„ธ์š”.

Llama.cpp๋กœ ์‚ฌ์šฉ๋ฒ• ์ƒ˜ํ”Œ

For simple inferencing, use a command similar to

./main -m gguf-q4_k_m.gguf --temp 0 --top-k 4 --prompt "who was Joseph Weizenbaum?"

Llama.cpp๋กœ ํ† ํฌ๋‚˜์ด์ง• ์ƒ˜ํ”Œ

To get a list of tokens, use a command similar to

./tokenization -m gguf-q4_k_m.gguf --prompt "who was Joseph Weizenbaum?"

Llama.cpp๋กœ ์ž„๋ฒ ๋”ฉ ์ƒ˜ํ”Œ

Text embeddings are calculated with a command similar to

./embedding -m gguf-q4_k_m.gguf --prompt "who was Joseph Weizenbaum?"

License

์›๋ณธ ๋ชจ๋ธ ๋ผ์ด์„ผ์Šค๋Š” Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0) ์ฐธ๊ณ ํ•˜์„ธ์š”.

Downloads last month
54
GGUF
Model size
1.44B params
Architecture
llama

3-bit

4-bit

8-bit

32-bit

Inference API
Unable to determine this model's library. Check the docs .