.env
Generic
TEXT_EMBEDDINGS_MODEL=sentence-transformers/all-MiniLM-L6-v2
TEXT_EMBEDDINGS_MODEL_TYPE=HF # LlamaCpp or HF
USE_MLOCK=false
Ingestion
PERSIST_DIRECTORY=db
DOCUMENTS_DIRECTORY=source_documents
INGEST_CHUNK_SIZE=500
INGEST_CHUNK_OVERLAP=50
INGEST_N_THREADS=3
Generation
MODEL_TYPE=LlamaCpp # GPT4All or LlamaCpp
MODEL_PATH=eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
MODEL_TEMP=0.8
MODEL_N_CTX=1024 # Max total size of prompt+answer
MODEL_MAX_TOKENS=256 # Max size of answer
MODEL_STOP=[STOP]
CHAIN_TYPE=betterstuff
N_RETRIEVE_DOCUMENTS=100 # How many documents to retrieve from the db
N_FORWARD_DOCUMENTS=100 # How many documents to forward to the LLM, chosen among those retrieved
N_GPU_LAYERS=4
Python version
Python 3.11.3
System
Ubuntu 22.04
CASALIOY version
ee9a4e5
Information
Related Components
Reproduction
docker run -it -p 8501:8501 -v /home/draeician/docker_files/models:/srv/CASALIOY/models --shm-size=16gb su77ungr/casalioy:stable /bin/bash
Literally I just mapped the volume in so I wouldn't have to download the models again.
(casalioy-py3.11) root@75d53b1f3f77:/srv/CASALIOY# python casalioy/startLLM.py
found local model dir at models/sentence-transformers/all-MiniLM-L6-v2
found local model file at models/eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
llama.cpp: loading model from models/eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
Fatal Python error: Illegal instruction
Current thread 0x00007f0012660740 (most recent call first):
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/llama_cpp/llama_cpp.py", line 183 in llama_init_from_file
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/llama_cpp/llama.py", line 157 in init
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/langchain/llms/llamacpp.py", line 133 in validate_environment
File "/srv/CASALIOY/casalioy/startLLM.py", line 57 in init
File "/srv/CASALIOY/casalioy/startLLM.py", line 123 in main
File "/srv/CASALIOY/casalioy/startLLM.py", line 135 in
Extension modules: grpc._cython.cygrpc, numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, pydantic.typing, pydantic.errors, pydantic.version, pydantic.utils, pydantic.class_validators, pydantic.config, pydantic.color, pydantic.datetime_parse, pydantic.validators, pydantic.networks, pydantic.types, pydantic.json, pydantic.error_wrappers, pydantic.fields, pydantic.parse, pydantic.schema, pydantic.main, pydantic.dataclasses, pydantic.annotated_types, pydantic.decorator, pydantic.env_settings, pydantic.tools, pydantic, yaml._yaml, multidict._multidict, yarl._quoting_c, aiohttp._helpers, aiohttp._http_writer, aiohttp._http_parser, aiohttp._websocket, frozenlist._frozenlist, tornado.speedups, sqlalchemy.cyextension.collections, sqlalchemy.cyextension.immutabledict, sqlalchemy.cyextension.processors, sqlalchemy.cyextension.resultproxy, sqlalchemy.cyextension.util, greenlet._greenlet, numexpr.interpreter, torch._C, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, scipy._lib._ccallback_c, numpy.linalg.lapack_lite, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.sparse.linalg._isolve._iterative, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg._cythonized_array_utils, scipy.linalg._flinalg, scipy.linalg._solve_toeplitz, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg.cython_lapack, scipy.linalg.cython_blas, scipy.linalg._matfuncs_expm, scipy.linalg._decomp_update, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, scipy.spatial._ckdtree, scipy._lib.messagestream, scipy.spatial._qhull, scipy.spatial._voronoi, scipy.spatial._distance_wrap, scipy.spatial._hausdorff, scipy.special._ufuncs_cxx, scipy.special._ufuncs, scipy.special._specfun, scipy.special._comb, scipy.special._ellip_harm_2, scipy.spatial.transform._rotation, scipy.ndimage._nd_image, _ni_label, scipy.ndimage._ni_label, scipy.optimize._minpack2, scipy.optimize._group_columns, scipy.optimize._trlib._trlib, scipy.optimize._lbfgsb, _moduleTNC, scipy.optimize._moduleTNC, scipy.optimize._cobyla, scipy.optimize._slsqp, scipy.optimize._minpack, scipy.optimize._lsq.givens_elimination, scipy.optimize._zeros, scipy.optimize.__nnls, scipy.optimize._highs.cython.src._highs_wrapper, scipy.optimize._highs._highs_wrapper, scipy.optimize._highs.cython.src._highs_constants, scipy.optimize._highs._highs_constants, scipy.linalg._interpolative, scipy.optimize._bglu_dense, scipy.optimize._lsap, scipy.optimize._direct, scipy.integrate._odepack, scipy.integrate._quadpack, scipy.integrate._vode, scipy.integrate._dop, scipy.integrate._lsoda, scipy.special.cython_special, scipy.stats._stats, scipy.stats.beta_ufunc, scipy.stats._boost.beta_ufunc, scipy.stats.binom_ufunc, scipy.stats._boost.binom_ufunc, scipy.stats.nbinom_ufunc, scipy.stats._boost.nbinom_ufunc, scipy.stats.hypergeom_ufunc, scipy.stats._boost.hypergeom_ufunc, scipy.stats.ncf_ufunc, scipy.stats._boost.ncf_ufunc, scipy.stats.ncx2_ufunc, scipy.stats._boost.ncx2_ufunc, scipy.stats.nct_ufunc, scipy.stats._boost.nct_ufunc, scipy.stats.skewnorm_ufunc, scipy.stats._boost.skewnorm_ufunc, scipy.stats.invgauss_ufunc, scipy.stats._boost.invgauss_ufunc, scipy.interpolate._fitpack, scipy.interpolate.dfitpack, scipy.interpolate._bspl, scipy.interpolate._ppoly, scipy.interpolate.interpnd, scipy.interpolate._rbfinterp_pythran, scipy.interpolate._rgi_cython, scipy.stats._biasedurn, scipy.stats._levy_stable.levyst, scipy.stats._stats_pythran, scipy._lib._uarray._uarray, scipy.stats._statlib, scipy.stats._mvn, scipy.stats._sobol, scipy.stats._qmc_cy, scipy.stats._rcont.rcont, regex._regex, sklearn.__check_build._check_build, sklearn.utils.murmurhash, sklearn.utils._isfinite, sklearn.utils._openmp_helpers, sklearn.utils._vector_sentinel, sklearn.feature_extraction._hashing_fast, sklearn.utils._logistic_sigmoid, sklearn.utils.sparsefuncs_fast, sklearn.preprocessing._csr_polynomial_expansion, sklearn.utils._cython_blas, sklearn.svm._libsvm, sklearn.svm._liblinear, sklearn.svm._libsvm_sparse, sklearn.utils._random, sklearn.utils._seq_dataset, sklearn.utils.arrayfuncs, sklearn.utils._typedefs, sklearn.utils._readonly_array_wrapper, sklearn.metrics._dist_metrics, sklearn.metrics.cluster._expected_mutual_info_fast, sklearn.metrics._pairwise_distances_reduction._datasets_pair, sklearn.metrics._pairwise_distances_reduction._base, sklearn.metrics._pairwise_distances_reduction._middle_term_computer, sklearn.utils._heap, sklearn.utils._sorting, sklearn.metrics._pairwise_distances_reduction._argkmin, sklearn.metrics._pairwise_distances_reduction._radius_neighbors, sklearn.metrics._pairwise_fast, sklearn.linear_model._cd_fast, sklearn._loss._loss, sklearn.utils._weight_vector, sklearn.linear_model._sgd_fast, sklearn.linear_model._sag_fast, sklearn.datasets._svmlight_format_fast, scipy.io.matlab._mio_utils, scipy.io.matlab._streams, scipy.io.matlab._mio5_utils, sentencepiece._sentencepiece, PIL._imaging (total: 201)
Illegal instruction (core dumped)
Expected behavior
Since this it the first time running this application, I was expecting a text interface to query the documents.
.env
Generic
TEXT_EMBEDDINGS_MODEL=sentence-transformers/all-MiniLM-L6-v2
TEXT_EMBEDDINGS_MODEL_TYPE=HF # LlamaCpp or HF
USE_MLOCK=false
Ingestion
PERSIST_DIRECTORY=db
DOCUMENTS_DIRECTORY=source_documents
INGEST_CHUNK_SIZE=500
INGEST_CHUNK_OVERLAP=50
INGEST_N_THREADS=3
Generation
MODEL_TYPE=LlamaCpp # GPT4All or LlamaCpp
MODEL_PATH=eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
MODEL_TEMP=0.8
MODEL_N_CTX=1024 # Max total size of prompt+answer
MODEL_MAX_TOKENS=256 # Max size of answer
MODEL_STOP=[STOP]
CHAIN_TYPE=betterstuff
N_RETRIEVE_DOCUMENTS=100 # How many documents to retrieve from the db
N_FORWARD_DOCUMENTS=100 # How many documents to forward to the LLM, chosen among those retrieved
N_GPU_LAYERS=4
Python version
Python 3.11.3
System
Ubuntu 22.04
CASALIOY version
ee9a4e5
Information
Related Components
Reproduction
docker run -it -p 8501:8501 -v /home/draeician/docker_files/models:/srv/CASALIOY/models --shm-size=16gb su77ungr/casalioy:stable /bin/bash
Literally I just mapped the volume in so I wouldn't have to download the models again.
(casalioy-py3.11) root@75d53b1f3f77:/srv/CASALIOY# python casalioy/startLLM.py
found local model dir at models/sentence-transformers/all-MiniLM-L6-v2
found local model file at models/eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
llama.cpp: loading model from models/eachadea/ggml-vicuna-7b-1.1/ggml-vic7b-q5_1.bin
Fatal Python error: Illegal instruction
Current thread 0x00007f0012660740 (most recent call first):
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/llama_cpp/llama_cpp.py", line 183 in llama_init_from_file
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/llama_cpp/llama.py", line 157 in init
File "/srv/CASALIOY/.venv/lib/python3.11/site-packages/langchain/llms/llamacpp.py", line 133 in validate_environment
File "/srv/CASALIOY/casalioy/startLLM.py", line 57 in init
File "/srv/CASALIOY/casalioy/startLLM.py", line 123 in main
File "/srv/CASALIOY/casalioy/startLLM.py", line 135 in
Extension modules: grpc._cython.cygrpc, numpy.core._multiarray_umath, numpy.core._multiarray_tests, numpy.linalg._umath_linalg, numpy.fft._pocketfft_internal, numpy.random._common, numpy.random.bit_generator, numpy.random._bounded_integers, numpy.random._mt19937, numpy.random.mtrand, numpy.random._philox, numpy.random._pcg64, numpy.random._sfc64, numpy.random._generator, pydantic.typing, pydantic.errors, pydantic.version, pydantic.utils, pydantic.class_validators, pydantic.config, pydantic.color, pydantic.datetime_parse, pydantic.validators, pydantic.networks, pydantic.types, pydantic.json, pydantic.error_wrappers, pydantic.fields, pydantic.parse, pydantic.schema, pydantic.main, pydantic.dataclasses, pydantic.annotated_types, pydantic.decorator, pydantic.env_settings, pydantic.tools, pydantic, yaml._yaml, multidict._multidict, yarl._quoting_c, aiohttp._helpers, aiohttp._http_writer, aiohttp._http_parser, aiohttp._websocket, frozenlist._frozenlist, tornado.speedups, sqlalchemy.cyextension.collections, sqlalchemy.cyextension.immutabledict, sqlalchemy.cyextension.processors, sqlalchemy.cyextension.resultproxy, sqlalchemy.cyextension.util, greenlet._greenlet, numexpr.interpreter, torch._C, torch._C._fft, torch._C._linalg, torch._C._nested, torch._C._nn, torch._C._sparse, torch._C._special, scipy._lib._ccallback_c, numpy.linalg.lapack_lite, scipy.sparse._sparsetools, _csparsetools, scipy.sparse._csparsetools, scipy.sparse.linalg._isolve._iterative, scipy.linalg._fblas, scipy.linalg._flapack, scipy.linalg._cythonized_array_utils, scipy.linalg._flinalg, scipy.linalg._solve_toeplitz, scipy.linalg._matfuncs_sqrtm_triu, scipy.linalg.cython_lapack, scipy.linalg.cython_blas, scipy.linalg._matfuncs_expm, scipy.linalg._decomp_update, scipy.sparse.linalg._dsolve._superlu, scipy.sparse.linalg._eigen.arpack._arpack, scipy.sparse.csgraph._tools, scipy.sparse.csgraph._shortest_path, scipy.sparse.csgraph._traversal, scipy.sparse.csgraph._min_spanning_tree, scipy.sparse.csgraph._flow, scipy.sparse.csgraph._matching, scipy.sparse.csgraph._reordering, scipy.spatial._ckdtree, scipy._lib.messagestream, scipy.spatial._qhull, scipy.spatial._voronoi, scipy.spatial._distance_wrap, scipy.spatial._hausdorff, scipy.special._ufuncs_cxx, scipy.special._ufuncs, scipy.special._specfun, scipy.special._comb, scipy.special._ellip_harm_2, scipy.spatial.transform._rotation, scipy.ndimage._nd_image, _ni_label, scipy.ndimage._ni_label, scipy.optimize._minpack2, scipy.optimize._group_columns, scipy.optimize._trlib._trlib, scipy.optimize._lbfgsb, _moduleTNC, scipy.optimize._moduleTNC, scipy.optimize._cobyla, scipy.optimize._slsqp, scipy.optimize._minpack, scipy.optimize._lsq.givens_elimination, scipy.optimize._zeros, scipy.optimize.__nnls, scipy.optimize._highs.cython.src._highs_wrapper, scipy.optimize._highs._highs_wrapper, scipy.optimize._highs.cython.src._highs_constants, scipy.optimize._highs._highs_constants, scipy.linalg._interpolative, scipy.optimize._bglu_dense, scipy.optimize._lsap, scipy.optimize._direct, scipy.integrate._odepack, scipy.integrate._quadpack, scipy.integrate._vode, scipy.integrate._dop, scipy.integrate._lsoda, scipy.special.cython_special, scipy.stats._stats, scipy.stats.beta_ufunc, scipy.stats._boost.beta_ufunc, scipy.stats.binom_ufunc, scipy.stats._boost.binom_ufunc, scipy.stats.nbinom_ufunc, scipy.stats._boost.nbinom_ufunc, scipy.stats.hypergeom_ufunc, scipy.stats._boost.hypergeom_ufunc, scipy.stats.ncf_ufunc, scipy.stats._boost.ncf_ufunc, scipy.stats.ncx2_ufunc, scipy.stats._boost.ncx2_ufunc, scipy.stats.nct_ufunc, scipy.stats._boost.nct_ufunc, scipy.stats.skewnorm_ufunc, scipy.stats._boost.skewnorm_ufunc, scipy.stats.invgauss_ufunc, scipy.stats._boost.invgauss_ufunc, scipy.interpolate._fitpack, scipy.interpolate.dfitpack, scipy.interpolate._bspl, scipy.interpolate._ppoly, scipy.interpolate.interpnd, scipy.interpolate._rbfinterp_pythran, scipy.interpolate._rgi_cython, scipy.stats._biasedurn, scipy.stats._levy_stable.levyst, scipy.stats._stats_pythran, scipy._lib._uarray._uarray, scipy.stats._statlib, scipy.stats._mvn, scipy.stats._sobol, scipy.stats._qmc_cy, scipy.stats._rcont.rcont, regex._regex, sklearn.__check_build._check_build, sklearn.utils.murmurhash, sklearn.utils._isfinite, sklearn.utils._openmp_helpers, sklearn.utils._vector_sentinel, sklearn.feature_extraction._hashing_fast, sklearn.utils._logistic_sigmoid, sklearn.utils.sparsefuncs_fast, sklearn.preprocessing._csr_polynomial_expansion, sklearn.utils._cython_blas, sklearn.svm._libsvm, sklearn.svm._liblinear, sklearn.svm._libsvm_sparse, sklearn.utils._random, sklearn.utils._seq_dataset, sklearn.utils.arrayfuncs, sklearn.utils._typedefs, sklearn.utils._readonly_array_wrapper, sklearn.metrics._dist_metrics, sklearn.metrics.cluster._expected_mutual_info_fast, sklearn.metrics._pairwise_distances_reduction._datasets_pair, sklearn.metrics._pairwise_distances_reduction._base, sklearn.metrics._pairwise_distances_reduction._middle_term_computer, sklearn.utils._heap, sklearn.utils._sorting, sklearn.metrics._pairwise_distances_reduction._argkmin, sklearn.metrics._pairwise_distances_reduction._radius_neighbors, sklearn.metrics._pairwise_fast, sklearn.linear_model._cd_fast, sklearn._loss._loss, sklearn.utils._weight_vector, sklearn.linear_model._sgd_fast, sklearn.linear_model._sag_fast, sklearn.datasets._svmlight_format_fast, scipy.io.matlab._mio_utils, scipy.io.matlab._streams, scipy.io.matlab._mio5_utils, sentencepiece._sentencepiece, PIL._imaging (total: 201)
Illegal instruction (core dumped)
Expected behavior
Since this it the first time running this application, I was expecting a text interface to query the documents.