openchat:7b-v3.5-1210-q4_K

openchat:7b-v3.5-1210-q4_K_M

390.7K Downloads Updated 2 years ago

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

ollama run openchat:7b-v3.5-1210-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "openchat:7b-v3.5-1210-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='openchat:7b-v3.5-1210-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'openchat:7b-v3.5-1210-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

c0f6439075b8 · 4.4GB ·

model

archllama

parameters7.24B

quantizationQ4_K_M

4.4GB

license

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

params

{ "stop": [ "<|endoftext|>", "<|end_of_turn|>" ] }

65B

template

{{ .System }}<|end_of_turn|>GPT4 Correct User: {{ .Prompt }}<|end_of_turn|>GPT4 Correct Assistant:

98B

Readme

OpenChat is set of open-source language models, fine-tuned with C-RLFT: a strategy inspired by offline reinforcement learning.

Updated to OpenChat-3.5-1210, this new version of the model model excels at coding tasks and scores very high on many open-source LLM benchmarks.

References

GitHub

HuggingFace