vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : sync gguf-llama.cpp with latest llama.cpp (#2608)

Browse source 
* llama : sync gguf-llama.cpp with latest llama.cpp

* minor : indentation + assert

* llama : refactor gguf_buffer and gguf_ctx_buffer

* llama : minor
This commit is contained in:
Georgi Gerganov 2023-08-14 16:28:44 +03:00 • committed by GitHub
parent 6f64b6c0f8
commit f00780b2ee
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 692 additions and 463 deletions
Download patch file Download diff file Expand all files Collapse all files

23
examples/gguf/gguf.cpp
View file

@ -8,14 +8,19 @@
#include <sstream>
#include <fstream>
#include <vector>
/*
#undef MIN
#undef MAX
#define MIN(a, b) ((a) < (b) ? (a) : (b))
#define MAX(a, b) ((a) > (b) ? (a) : (b))
template<typename T>
static std::string to_string(const T & val) {
std::stringstream ss;
ss << val;
return ss.str();
}
*/
void gguf_ex_write_str(std::ofstream & fout, const std::string & val) {
const int32_t n = val.size();
fout.write((const char *) &n, sizeof(n));
@ -377,28 +382,28 @@ bool gguf_ex_read_2(const std::string & fname) {
struct gguf_file file(fname.c_str(), "rb");
gguf_mmap data_mmap(&file, 0, false);
const int n_tensors = gguf_get_n_tensors(ctx);
for (int i = 0; i < n_tensors; ++i) {
const char * name = gguf_get_tensor_name(ctx, i);
const size_t offset = gguf_get_data_offset(ctx) + gguf_get_tensor_offset(ctx, i);
const char * name = gguf_get_tensor_name(ctx, i);
const size_t offset = gguf_get_data_offset(ctx) + gguf_get_tensor_offset(ctx, i);
struct ggml_tensor * cur = ggml_get_tensor(ctx_data, name);
cur->data = static_cast<char *>(data_mmap.addr) + offset;
// print first 10 elements
const float * data = (const float *) cur->data;
const float * data = (const float *) cur->data;
printf("%s data[:10] : ", name);
for (int j = 0; j < 10; ++j) {
for (int j = 0; j < MIN(10, ggml_nelements(cur)); ++j) {
printf("%f ", data[j]);
}
printf("\n\n");
}
fprintf(stdout, "%s: ctx_data size: %zu\n", __func__, ggml_get_mem_size(ctx_data));
fprintf(stdout, "%s: ctx_data size: %zu\n", __func__, ggml_get_mem_size(ctx_data));
ggml_free(ctx_data);
gguf_free(ctx);