run after install - error

[MasterDimmy]

Expected Behavior

all is ok

Current Behavior

error on run

Steps to Reproduce

Checking discussions database...
llama_model_load: loading model from './models/gpt4all-lora-quantized-ggml.bin' - please wait ...
llama_model_load: GPTQ model detected - are you sure n_parts should be 2? we normally expect it to be 1
llama_model_load: use '--n_parts 1' if necessary
llama_model_load: n_vocab = 32001
llama_model_load: n_ctx   = 512
llama_model_load: n_embd  = 5120
llama_model_load: n_mult  = 256
llama_model_load: n_head  = 40
llama_model_load: n_layer = 40
llama_model_load: n_rot   = 128
llama_model_load: f16     = 4
llama_model_load: n_ff    = 13824
llama_model_load: n_parts = 2
llama_model_load: type    = 2
llama_model_load: ggml map size = 9702.04 MB
llama_model_load: ggml ctx size = 101.25 KB
llama_model_load: mem required  = 11750.14 MB (+ 3216.00 MB per state)
llama_model_load: loading tensors from './models/gpt4all-lora-quantized-ggml.bin'
llama_model_load: model size =  9701.60 MB / num tensors = 363
llama_init_from_file: kv self size  =  800.00 MB
Traceback (most recent call last):
  File "D:\gpt4all\gpt4all-ui\app.py", line 468, in <module>
    bot = Gpt4AllWebUI(app, args)
  File "D:\gpt4all\gpt4all-ui\app.py", line 98, in __init__
    self.prepare_a_new_chatbot()
  File "D:\gpt4all\gpt4all-ui\app.py", line 114, in prepare_a_new_chatbot
    self.condition_chatbot()
  File "D:\gpt4all\gpt4all-ui\app.py", line 130, in condition_chatbot
    if self.db.does_last_discussion_have_messages():
  File "D:\gpt4all\gpt4all-ui\db.py", line 162, in does_last_discussion_have_messages
    last_message = self.select("SELECT * FROM message WHERE discussion_id=?", (last_discussion_id,), fetch_all=False)
  File "D:\gpt4all\gpt4all-ui\db.py", line 86, in select
    cursor = conn.execute(query, params)
sqlite3.InterfaceError: Error binding parameter 0 - probably unsupported type.

Possible Solution

fix sql code

Context

none

Screenshots

none

[MasterDimmy]

restart and it works, but error happens on the first run

[jakuta-tech]

I think you need to convert the ggml to ggjt

(env) root@AI:/home/gpt4all-ui# python app.py --host 192.168.0.180 --model gpt4all-lora-quantized-ggjt.bin Checking discussions database... llama_model_load: loading model from './models/gpt4all-lora-quantized-ggjt.bin' - please wait ...

I think the current version of this repo has fixed it.

[ParisNeo]

the problem is probably due to the migration to the new database format. this should be the last time we run into this problem as we have created a versionning system so in next upgrades, the system will upgrade the database.

Sorry for the inconvenience.