Epiculous_-_Fett-uccine-7B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Fett-uccine-7B - bnb 8bits

• Model creator: https://huggingface.co/Epiculous/
• Original model: https://huggingface.co/Epiculous/Fett-uccine-7B/

Original model description:

datasets:

• lemonilia/LimaRP
• grimulkan/theory-of-mind
• Epiculous/Gnosis tags:
• not-for-all-audiences license: agpl-3.0

---

Fett-uccine

This model is created by training Mistral base model on LimaRP (ShareGPT format provided by SAO), theory of mind, and gnosis(provided by jeiku).

The 8-bit lora was then merged into Mistral Instruct resulting in what you see here.

Works best with ChatML Instruct

This model is in honor of the SillyTavern community, keep being awesome!

Optimal Settings provided by Nitral:

{
    "temp": 5,
    "temperature_last": true,
    "top_p": 1,
    "top_k": 0,
    "top_a": 0,
    "tfs": 1,
    "epsilon_cutoff": 0,
    "eta_cutoff": 0,
    "typical_p": 1,
    "min_p": 0.05,
    "rep_pen": 1,
    "rep_pen_range": 0,
    "no_repeat_ngram_size": 0,
    "penalty_alpha": 0,
    "num_beams": 1,
    "length_penalty": 0,
    "min_length": 0,
    "encoder_rep_pen": 1,
    "freq_pen": 0,
    "presence_pen": 0,
    "do_sample": true,
    "early_stopping": false,
    "dynatemp": false,
    "min_temp": 1,
    "max_temp": 5,
    "dynatemp_exponent": 1,
    "smoothing_factor": 0.3,
    "add_bos_token": true,
    "truncation_length": 2048,
    "ban_eos_token": false,
    "skip_special_tokens": true,
    "streaming": false,
    "mirostat_mode": 0,
    "mirostat_tau": 5,
    "mirostat_eta": 0.1,
    "guidance_scale": 1,
    "negative_prompt": "",
    "grammar_string": "",
    "banned_tokens": "",
    "ignore_eos_token_aphrodite": false,
    "spaces_between_special_tokens_aphrodite": true,
    "sampler_order": [
        6,
        0,
        1,
        3,
        4,
        2,
        5
    ],
    "logit_bias": [],
    "n": 1,
    "rep_pen_size": 0,
    "genamt": 150,
    "max_length": 8192
}