ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. weaviate-client 3.19.2 requires requests<2.29.0,>=2.28.0, but you have requests 2.31.0 which is incompatible.

[torpac]

Im using w11 pro, i cant seem to solve this.

[torpac]

Using embedded DuckDB with persistence: data will be stored in: db llama.cpp: loading model from models/ggml-vic13b-uncensored-q4_0.bin error loading model: unknown (magic, version) combination: 67676a74, 00000003; is this really a GGML file? llama_init_from_file: failed to load model Traceback (most recent call last): File "C:\TCHT\privateGPT\privateGPT.py", line 76, in main() File "C:\TCHT\privateGPT\privateGPT.py", line 34, in main llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, callbacks=callbacks, verbose=False) File "pydantic\main.py", line 341, in pydantic.main.BaseModel.init pydantic.error_wrappers.ValidationError: 1 validation error for LlamaCpp root Could not load Llama model from path: models/ggml-vic13b-uncensored-q4_0.bin. Received error (type=value_error)

it is giving another error now..

[maozdemir]

You arr using an older model. You have to use a GGML v3 model.

[Matt-Miracle]

I am having a similar (if not exact) issue that @Torpac noted with a brand-new install of the TroubleChut PrivateGPT One-Line launcher.

I chose the Vicuna 13B Uncensored during my installation.

Launching privateGPT... Using embedded DuckDB with persistence: data will be stored in: db llama.cpp: loading model from models/ggml-vic13b-uncensored-q4_0.bin error loading model: unknown (magic, version) combination: 67676a74, 00000003; is this really a GGML file? llama_init_from_file: failed to load model Traceback (most recent call last): File "C:\TCHT\privateGPT\privateGPT.py", line 82, in main() File "C:\TCHT\privateGPT\privateGPT.py", line 36, in main llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, n_batch=model_n_batch, callbacks=callbacks, verbose=False) File "pydantic\main.py", line 341, in pydantic.main.BaseModel.init pydantic.error_wrappers.ValidationError: 1 validation error for LlamaCpp root Could not load Llama model from path: models/ggml-vic13b-uncensored-q4_0.bin. Received error (type=value_error)

---

TroubleChute One-Line installer:

Python exited with an error code. Did you see something about 'ModuleNotFoundError' above? (y/n):

System info if needed:

• HP ZZ820 Workstation
• 2x Intel Xeon E5-2690 @ 3 GHz
• 128 GB RAM
• Windows 10 Pro 22H2
• 2x Nvidia Quardro K5200 in SLI mode
• Installed on Local Disk C (Micron M5550 SSD)

You will need to explain the fix to me as if my knowledge of programming was from the Quick Basic and COBOL days (please). I am a Windows System admin and I know just enough to know I need assistance. :)

Thanks in advance.