ymertzanis/meltemi7b

ymertzanis/ meltemi7b:latest

761 Downloads Updated 2 years ago

Meltemi, the first Greek Large Language Model (LLM) trained by the Institute for Language and Speech Processing at Athena Research & Innovation Center. Meltemi is built on top of Mistral-7B, extending its capabilities for Greek.

ollama run ymertzanis/meltemi7b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ymertzanis/meltemi7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ymertzanis/meltemi7b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ymertzanis/meltemi7b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

1391ca345479 · 8.0GB ·

model

archllama

parameters7.48B

quantizationQ8_0

8.0GB

template

<|im_start|>system {{ .System }}<|im_end|> <|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assi

113B

system

Είσαι το Μελτέμι, ένα γλωσσικό μοντέλο για την ελληνικ�

506B

params

{ "stop": [ "<|im_start|>", "<|im_end|>" ] }

59B

Readme

Runs pretty good on my Windows 16GB RAM laptop, it barely works on my M1 8GB Air. Uses this GGUF file https://huggingface.co/NikolayKozloff/Meltemi-7B-v1-GGUF