When finished loading a model, everytime I typed in something and pressed Enter I got that error (tried with different models and got the same error). I'm on Windows 10, 64GB of RAM, an RTX 3060 with 12GB of VRAM. Here's part of the output:

Load Text Model OK: True Embedded Kobold Lite loaded. Embedded API docs loaded. Starting Kobold API on port 5001 at http://localhost:5001/api/ Starting OpenAI Compatible API on port 5001 at http://localhost:5001/v1/

Please connect to custom endpoint at http://localhost:5001

Input: {"n": 1, "max_context_length": 8192, "max_length": 2048, "rep_pen": 1.05, "temperature": 0.77, "top_p": 1, "top_k": 100, "top_a": 0, "typical": 1, "tfs": 0.93, "rep_pen_range": 404, "rep_pen_slope": 0.8, "sampler_order": [6, 0, 5, 3, 2, 1, 4], "memory": "you are a talkative assistant.\n\n", "genkey": "KCPP2306", "min_p": 0, "dynatemp_range": 0, "dynatemp_exponent": 1, "smoothing_factor": 0, "banned_tokens": [], "render_special": false, "presence_penalty": 0, "logit_bias": {}, "prompt": "<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nasdfasdf<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n", "quiet": true, "stop_sequence": ["<|eot_id|><|start_header_id|>user<|end_header_id|>", "<|eot_id|><|start_header_id|>assistant<|end_header_id|>"], "use_default_badwordsids": true, "bypass_eos": false}

(Warning! Request max_context_length=8192 exceeds allocated context size of 2048. It will be reduced to fit. Consider launching with increased --contextsize to avoid errors. This message will only show once per session.)

(Note: Sub-optimal sampler_order detected. You may have reduced quality. Recommended sampler values are [6,0,1,3,4,2,5]. This message will only show once per session.) [WinError -529697949] Windows Error 0xe06d7363

LostRuins / koboldcpp

WinError! #889

Load Text Model OK: True Embedded Kobold Lite loaded. Embedded API docs loaded. Starting Kobold API on port 5001 at http://localhost:5001/api/ Starting OpenAI Compatible API on port 5001 at http://localhost:5001/v1/