blackened/t-lite

blackened/ t-lite:latest

898 Downloads Updated 1 year ago

t-lite Model of T-bank rus https://t.me/machinelearning_rus/18728

ollama run blackened/t-lite

curl http://localhost:11434/api/chat \
  -d '{
    "model": "blackened/t-lite",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='blackened/t-lite',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'blackened/t-lite',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

f7dfa19f99d5 · 16GB ·

model

archllama

parameters8.03B

quantizationF16

16GB

template

{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

255B

Readme

Converted for Ollama by Evgeny Ryumin.

Specialists from the T-Bank Center for Artificial Intelligence have released a new language model in the 7-8 billion parameter range. According to internal and industry benchmarks, the model outperforms all existing counterparts in its class.

The T-lite model was introduced at the inaugural Turbo ML Conf, T-Bank’s first conference on machine learning. T-lite is a development tool that allows companies to create LLM applications for their own use without transferring data to third parties. These applications can include support assistants for handling requests, answering questions, etc. For example, an LLM can be used for voice-order processing.