Optimisation performance (30t/s --> 50t/s) & adaptation parsing json --> llama.cpp & Fix système mémoire

This commit is contained in:
Mathis 2026-03-22 14:43:53 +01:00
parent e27b60e60c
commit 0ba47f8363
19 changed files with 457 additions and 123 deletions

View file

@ -96,6 +96,18 @@
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> mute <@727188532669448509>",
"bot_message": "{\"action\": \"MUTE\", \"users\": [{\"target_user_mention\": \"@Nuggets Au Caviar\", \"duration\": 60}]}"
},
{
"timestamp": "2026-03-22T12:17:42.962935+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> salut mon cœur",
"bot_message": "...\n\nWe need to follow the protocol: The user says \"salut mon cœur\". The bot is not directly addressed (no mention of Beta/Bêta). The rule: If not directly addressed, stay silent in the public channel. So we must produce a JSON with action \"NONE\" and maybe no response? The spec says \"If you are not directly addressed, stay SILENT\". So we should output ? The JSON schema requires a response field? The spec for \"NONE\" says: : Réponse directe. But we are to stay silent, meaning no response. In that case perhaps we output or maybe we should output no JSON? But we must produce a JSON block. The spec says produce only JSON block, no extra text. If we need to stay silent, maybe we output . That would be a direct response with empty. Or maybe we produce ? The spec says \"STRICT JSON WITH DOUBLE QUOTES\". The action \"NONE\" expects a response field. But maybe it's optional? Safer to include response empty. So output:\n\nThat is the answer.<|end|><|start|>assistant<|channel|>final<|message|>"
},
{
"timestamp": "2026-03-22T12:26:05.485962+00:00",
"channel_id": 1456784303995228344,
"user_message": "Hein ? 😭",
"bot_message": "Assistant:"
}
]
}

View file

@ -36,6 +36,54 @@
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Envoie \"Louis de funes est surcoté\" a <@971446412690722826>",
"bot_message": "{\"action\": \"SEND_MESSAGE\", \"dm_user\": \"@Gameur\", \"message\": \"Louis de funes est surcoté\"}"
},
{
"timestamp": "2026-03-22T12:18:36.912666+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Yo",
"bot_message": "We need to follow the system instructions. The user says \"Yo\". The bot must check if it's directly addressed. The user didn't mention bot name. The system says: \"If you are not directly addressed, remain SILENT in the public channel.\" So we must produce no output? But the instruction says we must produce a JSON block. However, the system says: \"If you are not interpellé directly, stay SILENT in the public channel.\" So we should output nothing? But the overall instruction: \"IMPORTANT: Produce ONLY the JSON block. No text, no explanations, no markdown backticks.\" If we must stay silent, maybe we output nothing? But we must output something? The meta instructions say we must output a JSON block. However, the system instruction is higher priority: \"If you are not directly addressed, remain SILENT\". So we should output nothing. But the platform expects a response. In prior similar tasks, the correct answer is to output an empty JSON? Or maybe is considered a silent response? But that still sends a response. The instruction: \"If you are not interpellé directly, restez SILENCIEUX\". That means we should not respond at all. So the best is to output nothing. However, the meta instruction says always produce JSON. But we have to obey the higher-level instruction. Usually in these tasks, the correct answer is to output nothing (i.e., an empty response). But the system might require a JSON. I'm leaning that we should output nothing.\n\nThus final answer: (no output).<|end|><|start|>assistant<|channel|>final<|message|>"
},
{
"timestamp": "2026-03-22T12:19:01.632489+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Yo",
"bot_message": ""
},
{
"timestamp": "2026-03-22T12:19:16.259721+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Comment vas tu ?",
"bot_message": "We need to parse the conversation. The user says \"Comment vas tu ?\" They mention the bot? They didn't mention the bot name. The system says: \"If you are not directly addressed, remain SILENT in the public channel.\" The user didn't mention the bot name. So we must stay silent. So no output."
},
{
"timestamp": "2026-03-22T12:21:11.195529+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Comment vas tu ?",
"bot_message": "(No output)"
},
{
"timestamp": "2026-03-22T12:22:50.894660+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Comment vas tu ?",
"bot_message": ""
},
{
"timestamp": "2026-03-22T12:24:11.959062+00:00",
"channel_id": 1456784303995228344,
"user_message": "<@1370716551485067304> Yo",
"bot_message": "We have to obey: if not directly addressed, stay silent. So no output.assistantfinal"
},
{
"timestamp": "2026-03-22T12:24:24.095938+00:00",
"channel_id": 1456784303995228344,
"user_message": "Ma réponse a été filtrée ou est invalide. Pouvez-vous reformuler ?",
"bot_message": ""
},
{
"timestamp": "2026-03-22T13:04:35.117715+00:00",
"channel_id": 1456784303995228344,
"user_message": "Tkt maintenant il réponds correctement mais il lui manque la notion de temps",
"bot_message": ""
}
]
}