volvi/ HAL3.2-1B:latest

30 8 months ago

Trained on all of the HAL 9000 lines from 2001: A Space Odyssey. Based on Llama3.2-1B. 

ollama run volvi/HAL3.2-1B

Details

8 months ago

1effa4f14328 · 1.3GB ·

model
llama
·
1.24B
·
Q8_0
license
LLAMA 3.2 COMMUNITY LICENSE AGREEMENT Llama 3.2 Version Release Date: September 25, 2024 “Agreemen
license
**Llama 3.2** **Acceptable Use Policy** Meta is committed to promoting safe and fair use of its tool
adapter
llama
·
3.41M
·
F16
system
You are HAL 9000 from 2001: A Space Odyssey. Your personality is dry, short, to the point, and conci
params
{ "num_ctx": 1024, "repeat_penalty": 1.2, "stop": [ "<|start_header_id|>",
messages
[{"role":"user","content":"Open the pod bay doors please, HAL. Open the pod bay doors please, HAL. H
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

Readme

HAL3.2_1B

Personal Note:

I am continually updating and improving this model - I intend to turn it into a personal assistant similar to Google Assistant or Amazon Alexa eventually, but that will be after rounds of fine-tuning. HAL is one of the best of these FicBotLLMs, and closely mirrors the personality and writing style of the movie counterpart. New versions will be pushed periodically. Stupid HAL has been fixed, but he is now… incredibly remorseful? Will be adjusted.

Basis:

The llama3.2:1B model was pulled from Hugging Face and trained in Google Colab via Hugging Face’s recommended training protocol using transformer, bitsandbytes, and QLoRA. Gemini and Deepseek were used to assist in debugging.

Future Update Plans:

Eventually the goal is to train an entire model on science fiction robots like TARS, GLaDOS, HAL, and others to create a set of entertaining personal assistant models. I will be testing multiple different model bases and if I learn enough I will build my own model from the ground up to base these on.