privategpt-colab's People
privategpt-colab's Issues
cuda driver issue
https://huggingface.co/TheBloke/koala-7B-GGML/resolve/main/koala-7B.ggml.q4_0.bin
this is not available getting 404
https://huggingface.co/TheBloke/koala-7B-GGML/resolve/main/koala-7B.ggmlv3.q4_0.bin installed this version but getting error while running
Run the chatbot
!python3 privateGPT.py
Using embedded DuckDB with persistence: data will be stored in: db
CUDA error 35 at /content/llama-cpp-python/vendor/llama.cpp/ggml-cuda.cu:2106: CUDA driver version is insufficient for CUDA runtime version
what is an issue?
AttributeError: 'Llama' object has no attribute 'ctx'
Hi, I am trying to run this colab and gotten the error below when trying the run the chatbot. Do you have any idea on the cause?
# Run the chatbot !python3 privateGPT.py
Using embedded DuckDB with persistence: data will be stored in: db
ggml_init_cublas: found 1 CUDA devices:
Device 0: Tesla T4
Traceback (most recent call last):
File "/content/privateGPT/privateGPT.py", line 101, in
main()
File "/content/privateGPT/privateGPT.py", line 56, in main
llm = LlamaCpp(model_path=model_path, n_ctx=model_n_ctx, callbacks=callbacks, verbose=False, n_gpu_layers=calculate_layer_count())
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/koala-7B.ggml.q4_0.bin. Received error Model path does not exist: models/koala-7B.ggml.q4_0.bin (type=value_error)
Exception ignored in: <function Llama.del at 0x7f7f331283a0>
Traceback (most recent call last):
File "/usr/local/lib/python3.10/dist-packages/llama_cpp_python-0.1.59-py3.10-linux-x86_64.egg/llama_cpp/llama.py", line 1424, in del
if self.ctx is not None:
AttributeError: 'Llama' object has no attribute 'ctx'
Llamacpp not offloading on GPU
ggml_init_cublas: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090
llama.cpp: loading model from models/koala-7B.ggmlv3.q4_0.bin
llama_model_load_internal: format = ggjt v3 (latest)
llama_model_load_internal: n_vocab = 32000
llama_model_load_internal: n_ctx = 1000
llama_model_load_internal: n_embd = 4096
llama_model_load_internal: n_mult = 256
llama_model_load_internal: n_head = 32
llama_model_load_internal: n_layer = 32
llama_model_load_internal: n_rot = 128
llama_model_load_internal: ftype = 2 (mostly Q4_0)
llama_model_load_internal: n_ff = 11008
llama_model_load_internal: n_parts = 1
llama_model_load_internal: model size = 7B
llama_model_load_internal: ggml ctx size = 0.07 MB
llama_model_load_internal: using CUDA for GPU acceleration
llama_model_load_internal: mem required = 5407.71 MB (+ 1026.00 MB per state)
llama_model_load_internal: offloading 0 repeating layers to GPU
llama_model_load_internal: offloaded 0/35 layers to GPU
llama_model_load_internal: total VRAM used: 512 MB
issue on colab : !!kv_self.ctx
when i run the script, everything works fine.
except when i request my question.
# Run the chatbot
!python3 privateGPT.py
it gives :
Using embedded DuckDB with persistence: data will be stored in: db
ggml_init_cublas: found 1 CUDA devices:
Device 0: Tesla T4, compute capability 7.5
llama.cpp: loading model from models/koala-7B.ggmlv3.q5_0.bin
llama_model_load_internal: format = ggjt v3 (latest)
llama_model_load_internal: n_vocab = 32000
llama_model_load_internal: n_ctx = 1000
llama_model_load_internal: n_embd = 4096
llama_model_load_internal: n_mult = 256
llama_model_load_internal: n_head = 32
llama_model_load_internal: n_head_kv = 32
llama_model_load_internal: n_layer = 32
llama_model_load_internal: n_rot = 128
llama_model_load_internal: n_gqa = 1
llama_model_load_internal: rnorm_eps = 5.0e-06
llama_model_load_internal: n_ff = 11008
llama_model_load_internal: freq_base = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype = 8 (mostly Q5_0)
llama_model_load_internal: model size = 7B
who is Kafka ?
LLAMA_ASSERT: /content/llama-cpp-python/vendor/llama.cpp/llama.cpp:1800: !!kv_self.ctx
it display this line : LLAMA_ASSERT: /content/llama-cpp-python/vendor/llama.cpp/llama.cpp:1800: !!kv_self.ctx
without any answer.
i guest it crashes on qa(query)
.
Could not load Llama from path
Hi, can you help me?
I have issue when run chatbot :
%cd /content/privateGPT/
!python3 privateGPT.py
and get errors:
".....
root
Could not load Llama model from path : models/koadla-7B.ggmlv3.q4_0.bin ...."
Thank you in advance
Infinite looping in privateGPT.py
Hi, I run the privateGPT.py successfully and could get into "Enter a Query:".
I managed to type in the prompt but it doesn't give me any completion nor error, it just keeps loading for long time. Do you have any clue?
This is my value in .env
!sed -i 's/n_gpu_layers=10' /content/privateGPT/.env
!sed -i 's/MODEL_TYPE=GPT4All' /content/privateGPT/.env
!sed -i 's/ggml-gpt4all-j-v1.3-groovy.bin' /content/privateGPT/.env
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.