autogpt4all
autogpt4all copied to clipboard
Published
20 hours ago •
aorumbayev
aorumbayev
Can't compile go-bert.cpp, go-llama.cpp, bloomz.cpp etc.
I installed everything step by step. I tried an seperated Container but same there.
I get following message when running the autogpt4all.py or .sh
root@d2c36eb3a44c:/home/autogpt4all# python3 autogpt4all.py
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
golang is already the newest version (2:1.18~0ubuntu2).
cmake is already the newest version (3.22.1-1ubuntu1.22.04.1).
0 upgraded, 0 newly installed, 0 to remove and 0 not upgraded.
Already up to date.
go mod edit -replace github.com/go-skynet/go-llama.cpp=/home/autogpt4all/LocalAI/go-llama
go mod edit -replace github.com/nomic-ai/gpt4all/gpt4all-bindings/golang=/home/autogpt4all/LocalAI/gpt4all/gpt4all-bindings/golang
go mod edit -replace github.com/go-skynet/go-ggml-transformers.cpp=/home/autogpt4all/LocalAI/go-ggml-transformers
go mod edit -replace github.com/donomii/go-rwkv.cpp=/home/autogpt4all/LocalAI/go-rwkv
go mod edit -replace github.com/ggerganov/whisper.cpp=/home/autogpt4all/LocalAI/whisper.cpp
go mod edit -replace github.com/go-skynet/go-bert.cpp=/home/autogpt4all/LocalAI/go-bert
go mod edit -replace github.com/go-skynet/bloomz.cpp=/home/autogpt4all/LocalAI/bloomz
go mod edit -replace github.com/mudler/go-stable-diffusion=/home/autogpt4all/LocalAI/go-stable-diffusion
go mod edit -replace github.com/mudler/go-piper=/home/autogpt4all/LocalAI/go-piper
go mod download
touch prepare
I local-ai build info:
I BUILD_TYPE:
I GO_TAGS:
I LD_FLAGS: -X "github.com/go-skynet/LocalAI/internal.Version=v1.20.1-4-ga6839fd-dirty" -X "github.com/go-skynet/LocalAI/internal.Commit=a6839fd23827672aeab5988b344a2a34d7e44e6a"
CGO_LDFLAGS="" C_INCLUDE_PATH=/home/autogpt4all/LocalAI/go-llama:/home/autogpt4all/LocalAI/go-stable-diffusion/:/home/autogpt4all/LocalAI/gpt4all/gpt4all-bindings/golang/:/home/autogpt4all/LocalAI/go-ggml-transformers:/home/autogpt4all/LocalAI/go-rwkv:/home/autogpt4all/LocalAI/whisper.cpp:/home/autogpt4all/LocalAI/go-bert:/home/autogpt4all/LocalAI/bloomz LIBRARY_PATH=/home/autogpt4all/LocalAI/go-piper:/home/autogpt4all/LocalAI/go-llama:/home/autogpt4all/LocalAI/go-stable-diffusion/:/home/autogpt4all/LocalAI/gpt4all/gpt4all-bindings/golang/:/home/autogpt4all/LocalAI/go-ggml-transformers:/home/autogpt4all/LocalAI/go-rwkv:/home/autogpt4all/LocalAI/whisper.cpp:/home/autogpt4all/LocalAI/go-bert:/home/autogpt4all/LocalAI/bloomz go build -ldflags "-X "github.com/go-skynet/LocalAI/internal.Version=v1.20.1-4-ga6839fd-dirty" -X "github.com/go-skynet/LocalAI/internal.Commit=a6839fd23827672aeab5988b344a2a34d7e44e6a"" -tags "" -o local-ai ./
# github.com/go-skynet/go-bert.cpp
In file included from gobert.cpp:6:
go-bert/bert.cpp/bert.cpp: In function 'bert_ctx* bert_load_from_file(const char*)':
go-bert/bert.cpp/bert.cpp:610:89: warning: format '%lld' expects argument of type 'long long int', but argument 5 has type 'int64_t' {aka 'long int'} [-Wformat=]
610 | fprintf(stderr, "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%lld, %lld]\n",
| ~~~^
| |
| long long int
| %ld
611 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
go-bert/bert.cpp/bert.cpp:610:95: warning: format '%lld' expects argument of type 'long long int', but argument 6 has type 'int64_t' {aka 'long int'} [-Wformat=]
610 | fprintf(stderr, "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%lld, %lld]\n",
| ~~~^
| |
| long long int
| %ld
611 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
go-bert/bert.cpp/bert.cpp:610:112: warning: format '%lld' expects argument of type 'long long int', but argument 7 has type 'int64_t' {aka 'long int'} [-Wformat=]
610 | fprintf(stderr, "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%lld, %lld]\n",
| ~~~^
| |
| long long int
| %ld
611 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~
| |
| int64_t {aka long int}
go-bert/bert.cpp/bert.cpp:610:118: warning: format '%lld' expects argument of type 'long long int', but argument 8 has type 'int64_t' {aka 'long int'} [-Wformat=]
610 | fprintf(stderr, "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%lld, %lld]\n",
| ~~~^
| |
| long long int
| %ld
611 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~
| |
| int64_t {aka long int}
go-bert/bert.cpp/bert.cpp:624:37: warning: format '%lld' expects argument of type 'long long int', but argument 3 has type 'int64_t' {aka 'long int'} [-Wformat=]
624 | printf("%24s - [%5lld, %5lld], type = %6s, %6.2f MB, %9zu bytes\n", name.data(), ne[0], ne[1], ftype_str[ftype], ggml_bert_nbytes(tensor) / 1024.0 / 1024.0, ggml_bert_nbytes(tensor));
| ~~~~^ ~~~~~
| | |
| long long int int64_t {aka long int}
| %5ld
go-bert/bert.cpp/bert.cpp:624:44: warning: format '%lld' expects argument of type 'long long int', but argument 4 has type 'int64_t' {aka 'long int'} [-Wformat=]
624 | printf("%24s - [%5lld, %5lld], type = %6s, %6.2f MB, %9zu bytes\n", name.data(), ne[0], ne[1], ftype_str[ftype], ggml_bert_nbytes(tensor) / 1024.0 / 1024.0, ggml_bert_nbytes(tensor));
| ~~~~^ ~~~~~
| | |
| long long int int64_t {aka long int}
| %5ld
go-bert/bert.cpp/bert.cpp:655:101: warning: format '%llu' expects argument of type 'long long unsigned int', but argument 6 has type 'long unsigned int' [-Wformat=]
655 | fprintf(stderr, "%s: tensor '%s' has wrong size in model file: got %zu, expected %llu\n",
| ~~~^
| |
| long long unsigned int
| %lu
656 | __func__, name.data(), ggml_bert_nbytes(tensor), nelements * bpe);
| ~~~~~~~~~~~~~~~
| |
| long unsigned int
go-bert/bert.cpp/bert.cpp:692:32: warning: format '%d' expects argument of type 'int', but argument 3 has type 'size_t' {aka 'long unsigned int'} [-Wformat=]
692 | printf("%s: mem_per_token %d KB, mem_per_input %lld MB\n", __func__, new_bert->mem_per_token / (1 << 10), new_bert->mem_per_input / (1 << 20));
| ~^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
| | |
| int size_t {aka long unsigned int}
| %ld
go-bert/bert.cpp/bert.cpp:692:55: warning: format '%lld' expects argument of type 'long long int', but argument 4 has type 'int64_t' {aka 'long int'} [-Wformat=]
692 | printf("%s: mem_per_token %d KB, mem_per_input %lld MB\n", __func__, new_bert->mem_per_token / (1 << 10), new_bert->mem_per_input / (1 << 20));
| ~~~^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
| | |
| long long int int64_t {aka long int}
| %ld
# github.com/go-skynet/go-llama.cpp
binding.cpp: In function 'void* load_model(const char*, int, int, bool, bool, bool, bool, bool, bool, int, int, const char*, const char*, bool)':
binding.cpp:634:35: warning: 'llama_context* llama_init_from_file(const char*, llama_context_params*)' is deprecated: please use llama_load_model_from_file combined with llama_new_context_with_model instead [-Wdeprecated-declarations]
634 | res = llama_init_from_file(fname, &lparams);
| ~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~
In file included from go-llama/llama.cpp/examples/common.h:5,
from binding.cpp:1:
go-llama/llama.cpp/llama.h:164:49: note: declared here
164 | LLAMA_API DEPRECATED(struct llama_context * llama_init_from_file(
| ^~~~~~~~~~~~~~~~~~~~
go-llama/llama.cpp/llama.h:30:36: note: in definition of macro 'DEPRECATED'
30 | # define DEPRECATED(func, hint) func __attribute__((deprecated(hint)))
| ^~~~
# github.com/go-skynet/bloomz.cpp
bloomz.cpp: In function 'bool bloom_model_load(const string&, bloom_model&, gpt_bloomz_vocab&, int)':
bloomz.cpp:432:89: warning: format '%lld' expects argument of type 'long long int', but argument 5 has type 'int64_t' {aka 'long int'} [-Wformat=]
432 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
433 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
bloomz.cpp:432:95: warning: format '%lld' expects argument of type 'long long int', but argument 6 has type 'int64_t' {aka 'long int'} [-Wformat=]
432 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
433 | __func__, name.data(), tensor->ne[0], tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
bloomz.cpp:440:93: warning: format '%lld' expects argument of type 'long long int', but argument 5 has type 'int64_t' {aka 'long int'} [-Wformat=]
440 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
441 | __func__, name.data(), tensor->ne[0] / n_parts, tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~~~~~~~~~~~
| |
| int64_t {aka long int}
bloomz.cpp:440:99: warning: format '%lld' expects argument of type 'long long int', but argument 6 has type 'int64_t' {aka 'long int'} [-Wformat=]
440 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
441 | __func__, name.data(), tensor->ne[0] / n_parts, tensor->ne[1], ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
bloomz.cpp:447:93: warning: format '%lld' expects argument of type 'long long int', but argument 5 has type 'int64_t' {aka 'long int'} [-Wformat=]
447 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
448 | __func__, name.data(), tensor->ne[0], tensor->ne[1] / n_parts, ne[0], ne[1]);
| ~~~~~~~~~~~~~
| |
| int64_t {aka long int}
bloomz.cpp:447:99: warning: format '%lld' expects argument of type 'long long int', but argument 6 has type 'int64_t' {aka 'long int'} [-Wformat=]
447 | "%s: tensor '%s' has wrong shape in model file: got [%lld, %lld], expected [%d, %d]\n",
| ~~~^
| |
| long long int
| %ld
448 | __func__, name.data(), tensor->ne[0], tensor->ne[1] / n_parts, ne[0], ne[1]);
| ~~~~~~~~~~~~~~~~~~~~~~~
| |
| int64_t {aka long int}
# github.com/go-skynet/go-ggml-transformers.cpp
In file included from replit.cpp:21:
ggml.cpp/examples/replit/main.cpp: In function 'bool replit_model_load(const string&, replit_model&, replit_tokenizer&)':
ggml.cpp/examples/replit/main.cpp:345:56: warning: format '%lld' expects argument of type 'long long int', but argument 4 has type 'long int' [-Wformat=]
345 | printf("%s: memory_size = %8.2f MB, n_mem = %lld\n", __func__, memory_size / 1024.0 / 1024.0, n_mem);
| ~~~^ ~~~~~
| | |
| long long int long int
| %ld
replit.cpp: In function 'int replit_predict(void*, void*, char*)':
replit.cpp:65:31: warning: format '%d' expects argument of type 'int', but argument 4 has type '__gnu_cxx::__alloc_traits<std::allocator<long unsigned int>, long unsigned int>::value_type' {aka 'long unsigned int'} [-Wformat=]
65 | printf("%s: token[%d] = %6d\n", __func__, i, embd_inp[i]);
| ~~^
| |
| int
| %6ld
Already up to date.
