simonw / llm-gpt4all

Plugin for LLM adding support for the GPT4All collection of models
Apache License 2.0
218 stars 20 forks source link

GLIBCXX_3.4.26 not found on Linux using Conda #6

Open oostopitre opened 1 year ago

oostopitre commented 1 year ago

Running llm -m orca-mini-7b '3 names for a pet cow' gives the following error:

OSError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.26' not 
found (required by ~/miniconda3/envs/play/lib/python3.11/site-packages/gpt4all/llmodel_DO_NOT_MODIFY/build/libllmodel.so)

Env setup steps

conda create --name test_env python=3.11.4
conda activate test_env

pip install pandas==1.5.3
pip install gradio==3.36.1
pip install ipdb==0.13.13
pip install ipython==8.12.0
pip install llm==0.5.0

llm install llm-gpt4all

Based on the error, after trying to update some c-dependencies as suggested by stackoverflow posts

conda install libgcc

Now running llm -m orca-mini-7b '3 names for a pet cow' gives the following error Error: Unable to instantiate model

ENV:

active environment : test_env
          conda version : 23.5.2
    conda-build version : not installed
         python version : 3.11.4
       virtual packages : __archspec=1=x86_64
                          __glibc=2.26=0
                          __linux=5.4.247=0
                          __unix=0=0
               platform : linux-64
             user-agent : conda/23.5.2 requests/2.28.1 CPython/3.9.16 Linux/5.4.247-169.350.amzn2int.x86_64 amzn/2 glibc/2.26
                UID:GID : 13703959:100
           offline mode : False

Anyone found this error? The same setup steps run perfectly fine on a Mac OSX.

oostopitre commented 1 year ago

Looks like my CPU also supports avx and avxx instructions needed by gpt4all models

Architecture:        x86_64
CPU op-mode(s):      32-bit, 64-bit
Byte Order:          Little Endian
CPU(s):              8
On-line CPU(s) list: 0-7
Thread(s) per core:  2
Core(s) per socket:  4
Socket(s):           1
NUMA node(s):        1
Vendor ID:           GenuineIntel
CPU family:          6
Model:               79
Model name:          Intel(R) Xeon(R) CPU E5-2686 v4 @ 2.30GHz
Stepping:            1
CPU MHz:             2300.056
BogoMIPS:            4600.08
Hypervisor vendor:   Xen
Virtualization type: full
L1d cache:           32K
L1i cache:           32K
L2 cache:            256K
L3 cache:            46080K
NUMA node0 CPU(s):   0-7
Flags:              
 fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca 
cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx pdpe1gb 
rdtscp lm constant_tsc rep_good nopl xtopology cpuid pni pclmulqdq 
ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer 
aes xsave 
avx f16c rdrand hypervisor lahf_lm abm cpuid_fault invpcid_single
pti fsgsbase bmi1 
avx2 smep bmi2 erms invpcid xsaveopt