alfred:40b-1023-q4

alfred:40b-1023-q4_1

88.7K Downloads Updated 2 years ago

A robust conversational model designed to be used for both chat and instruct use cases.

40b

ollama run alfred:40b-1023-q4_1

curl http://localhost:11434/api/chat \
  -d '{
    "model": "alfred:40b-1023-q4_1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='alfred:40b-1023-q4_1',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'alfred:40b-1023-q4_1',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 years ago

2 years ago

d84e435512e7 · 26GB ·

model

archfalcon

parameters41.8B

quantizationQ4_1

26GB

template

<start_system>{{ .System }}<end_message><start_user>{{ .Prompt }}<end_message><start_assistant>

95B

system

You are Alfred, a helpful assistant trained by LightOn.

56B

params

{ "stop": [ "<end_message>", "</end_message>", "<start_user>", "

201B

Readme

Alfred is a robust conversational model created by LightOn, based on the Falcon 40B model. It’s designed to be used for both chat and instruct use cases.

Some of its features include:

Reduced Hallucinations: ability to minimize hallucinations, ensuring more accurate and reliable outputs.
Enhanced Self-Awareness: In situations where the model lacks a definitive answer, Alfred-40B-1023 is now programmed to state, “I don’t know”, enhancing its transparency and trustworthiness.
Superior ‘Chat with Docs’ Capability: Alfred-40B-1023 is trained to perform ‘Chat with Docs’ tasks like no other, streamlining document interaction and information retrieval.
Expanded Context: With an increased context of 8K tokens, Alfred-40B-1023 can comprehend and generate longer and more intricate content, ensuring detailed and comprehensive responses.

References

HuggingFace

Blog Post

Alfred is a robust conversational model created by LightOn, based on the [Falcon](https://ollama.ai/library/falcon) 40B model. It's designed to be used for both chat and instruct use cases.

Some of its features include:

* Reduced Hallucinations: ability to minimize hallucinations, ensuring more accurate and reliable outputs.
* Enhanced Self-Awareness: In situations where the model lacks a definitive answer, Alfred-40B-1023 is now programmed to state, "I don't know", enhancing its transparency and trustworthiness.
* Superior 'Chat with Docs' Capability: Alfred-40B-1023 is trained to perform 'Chat with Docs' tasks like no other, streamlining document interaction and information retrieval.
* Expanded Context: With an increased context of 8K tokens, Alfred-40B-1023 can comprehend and generate longer and more intricate content, ensuring detailed and comprehensive responses.

## References

[HuggingFace](https://huggingface.co/lightonai/alfred-40b-1023)

[Blog Post](https://www.lighton.ai/blog/lighton-s-blog-4/alfred-40b-1023-44)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)