|
--- |
|
license: llama2 |
|
datasets: |
|
- totally-not-an-llm/EverythingLM-data-V2 |
|
--- |
|
|
|
# EverythingLM-13b-16k |
|
|
|
Introducing EverythingLM, a llama-2 based, general-purpose 13b model with 16k context thanks to LlongMa. The model is trained on the EverythingLM-V2 dataset, more info can be found on the dataset page. |
|
|
|
The model is completely uncensored. |
|
|
|
### GGML quants: |
|
soon |
|
|
|
Make sure to use correct rope scaling settings: |
|
`-c 16384 --rope-freq-base 10000 --rope-freq-scale 0.25` |
|
### GPTQ quants: |
|
soon |
|
|
|
### Notable features: |
|
- Automatically triggered CoT reasoning. |
|
- Verbose and detailed replies. |
|
- Creative stories. |
|
- Better prompt understanding. |
|
|
|
### Prompt format: |
|
It is a modified Vicuna format, the same used in many of ehartford's models. |
|
``` |
|
You are a helpful AI assistant. |
|
|
|
USER: <prompt> |
|
ASSISTANT: |
|
``` |
|
|
|
Training took about 2.5 hours using QLoRa on 1xA100, so this model can be recreated for about $4. QLoRa model can be found here: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-V2-peft. |
|
|
|
### Future plans: |
|
- Native finetune. |
|
- Other model sizes. |
|
- Test some model merges using this model. (Specifically OpenOrca and Platypus models) |
