Sao10K/

L3-8B-Chara-v1-Alpha

- Don't expect this to beat Stheno or other mature models. It won't.
- Works best when in group chat scenarios, with properly defined cards, I think it is a successful test?
- A very small dataset of varying quality (human data) was used. Does not work well outside of its specified scenario.

- Uses L3-Instruct Format.
- One designated character per entry is the Human-turn, while all other characters are different, assigned GPT-turns, not in order to simulate real group chats.
- Per entry, it varies from 2-5 Unique Characters usually.
- There is roughly only ~3K sample entries.
- May not be the smartest due to all samples being roleplay / conversational data.

- 1 on 1 RP Performance might be Affected as focus is solely on group chats.
- The names may be multiple tokens instead of one token as they replace User / Assistant -> May Affect Output Quality -> Another Idea is in the works.
- Dataset Quality? While it is filtered, a few times... there's still the occasional low quality in there. I have not gone through a manual pass, this is a proof of concept.

    {
        "token_length": x,
        "Unique_chars": 3,
        "conversations": [
            {
                "from": "system",
                "value": "text"
            },
            {
                "from": "human-chat",
                "name": "User-1",
                "value": "text"
            },
            {
                "from": "gpt-chat",
                "name": "User-2",
                "value": "text"
            },
            {
                "from": "human-chat",
                "name": "User-1",
                "value": "text"
            },
            {
                "from": "gpt-chat",
                "name": "User-3",
                "value": "text"
            },
            {
                "from": "human-chat",
                "name": "User-1",
                "value": "text"
            },
            {
                "from": "gpt-chat",
                "name": "User-2",
                "value": "text"
            },
            {
                "from": "gpt-chat",
                "name": "User-3",
                "value": "text"
            }
        ]
    },