I'm trying to default to the "Chat Mode" format, I'm able to send generate requests as shown in the API docs, but if I replicate with my own client application the JSON that is sent in Chat Mode sessions I get Body Err: b, yet if I use the exact same JSON with the "Try it out" function it sends correctly
Here is the error:
Body Err: b'{"n": 1, "max_context_length": 1600, "max_length": 120, "rep_pen": 1.1, "temperature": 0.7, "top_p": 0.92, "top_k": 100, "top_a": 0, "typical": 1, "tfs": 1, "rep_pen_range": 320, "rep_pen_slope": 0.7, "sampler_order": [6, 0, 1, 3, 4, 2, 5], "memory": "", "genkey": "KCPP6833", "min_p": 0, "presence_penalty": 0, "logit_bias": {}, "prompt": "[The following is an interesting chat message log between You and KoboldAI.]\n\nYou: Hi.\nKoboldAI: Hello.\nYou: What is KoboldAI?\nKoboldAI:", "quiet": true, "stop_sequence": ["You:", "\nYou ", "\nKoboldAI: "], "use_default_badwordsids": false}'
Any ideas whi it doesn't work in my application but it does with the "Try it out" function?
I'm trying to default to the "Chat Mode" format, I'm able to send generate requests as shown in the API docs, but if I replicate with my own client application the JSON that is sent in Chat Mode sessions I get
Body Err: b, yet if I use the exact same JSON with the "Try it out" function it sends correctlyHere is the error:
Body Err: b'{"n": 1, "max_context_length": 1600, "max_length": 120, "rep_pen": 1.1, "temperature": 0.7, "top_p": 0.92, "top_k": 100, "top_a": 0, "typical": 1, "tfs": 1, "rep_pen_range": 320, "rep_pen_slope": 0.7, "sampler_order": [6, 0, 1, 3, 4, 2, 5], "memory": "", "genkey": "KCPP6833", "min_p": 0, "presence_penalty": 0, "logit_bias": {}, "prompt": "[The following is an interesting chat message log between You and KoboldAI.]\n\nYou: Hi.\nKoboldAI: Hello.\nYou: What is KoboldAI?\nKoboldAI:", "quiet": true, "stop_sequence": ["You:", "\nYou ", "\nKoboldAI: "], "use_default_badwordsids": false}'Any ideas whi it doesn't work in my application but it does with the "Try it out" function?