rscr/llama3_70b

rscr/ llama3_70b_ru:latest

26 Downloads Updated 2 years ago

Llama3-70B-EnSecAI-Ru-Chat

tools

ollama run rscr/llama3_70b_ru

curl http://localhost:11434/api/chat \
  -d '{
    "model": "rscr/llama3_70b_ru",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='rscr/llama3_70b_ru',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'rscr/llama3_70b_ru',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

7a28ac8b844c · 141GB

model

archllama

parameters70.6B

quantizationF16

141GB

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"

96B

template

{{ if .Messages }} {{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> {{- if .Sys

1.7kB

Readme

Fp16 (latest): HF i1-Q4_K_M: HF Q4_K_M: Quantized using Ollama

SOTA Russian model on MERA benchmark

Generation parameters: -temperature=0.6 -top_p=0.9