1

I am getting this error, could anyone please help to resolve it?

PS C:\Users\name\Desktop\privateGPT-main\privateGPT-main> python privateGPT.py Found model file at models/ggml-gpt4all-j-v1.3-groovy.bin gptj_model_load: loading model from 'models/ggml-gpt4all-j-v1.3-groovy.bin' - please wait ...

gptj_model_load: n_vocab = 50400
gptj_model_load: n_ctx = 2048
gptj_model_load: n_embd = 4096
gptj_model_load: n_head = 16
gptj_model_load: n_layer = 28
gptj_model_load: n_rot = 64
gptj_model_load: f16 = 2
gptj_model_load: ggml ctx size = 5401.45 MB
gptj_model_load: kv self size = 896.00 MB
gptj_model_load: ................................... done
gptj_model_load: model size = 3609.38 MB / num tensors = 285
Traceback (most recent call last):
File "C:\Users\name\Desktop\privateGPT-main\privateGPT-main\privateGPT.py", line 83, in
main()
File "C:\Users\name\Desktop\privateGPT-main\privateGPT-main\privateGPT.py", line 38, in main
llm = GPT4All(model=model_path, n_ctx=model_n_ctx, backend='gptj', n_batch=model_n_batch, callbacks=callbacks, verbose=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\name\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain\load\serializable.py", line 74, in init
super().init(**kwargs)
File "pydantic\main.py", line 341, in pydantic.main.BaseModel.init
pydantic.error_wrappers.ValidationError: 1 validation error for GPT4All
n_ctx
extra fields not permitted (type=value_error.extra)

PERSIST_DIRECTORY=db
MODEL_TYPE=GPT4All
MODEL_PATH=models/ggml-gpt4all-j-v1.3-groovy.bin
EMBEDDINGS_MODEL_NAME=all-MiniLM-L6-v2
MODEL_N_CTX=1000
MODEL_N_BATCH=8
TARGET_SOURCE_CHUNKS=4
Franck Dernoncourt
  • 77,520
  • 72
  • 342
  • 501
Saravanan Baskar
  • 13
  • 4
  • Some [bug](https://github.com/hwchase17/langchain/issues/1497) [reports](https://github.com/hwchase17/langchain/issues/6635) on Github suggest that you may need to run `pip install -U langchain` regularly and then make sure your code matches the current version of the class due to rapid changes. Sharing the relevant code in your script in addition to just the output would also be helpful – nigh_anxiety Jul 12 '23 at 19:00

2 Answers2

1

While Suresh's initial response provided partial assistance, I encountered another error subsequently, prompting me to seek an alternative solution. Thankfully, on GitHub, I found a useful suggestion by user adrisalcedo00, advising the installation of "langchain"

pip install git+https://github.com/hwchase17/langchain.git

And recommending the modification of the "n_ctx" parameter to "max_tokens" in the "GPT4All" case:

case "GPT4All":
    llm = GPT4All(model=model_path, max_tokens=model_n_ctx, backend='gptj', n_batch=model_n_batch, callbacks=callbacks, verbose=False)

Following this advice, I was able to resolve the issue successfully.

Roman Losev
  • 1,911
  • 19
  • 26
0

Just Use the old version pip install -U langchain==0.0.197

suresh
  • 26
  • 1