gguf : start implementing quantization (WIP)

examples/gguf/gguf.cpp

@@ -421,7 +421,7 @@ int main(int argc, char ** argv) {
         GGML_ASSERT(gguf_ex_write(fname) && "failed to write gguf file");
     } else if (mode == "r") {
         GGML_ASSERT(gguf_ex_read_0(fname) && "failed to read gguf file");
-        GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
+        //GGML_ASSERT(gguf_ex_read_1(fname) && "failed to read gguf file");
         GGML_ASSERT(gguf_ex_read_2(fname) && "failed to read gguf file");
     } else if (mode == "q") {
         llama_model_quantize_params params = llama_model_quantize_default_params();

gguf-llama.cpp

@@ -527,7 +527,7 @@ struct ggml_context * ctx_data = NULL;
         // TODO: read all hparams from file
         int q_ver_idx = gguf_find_key (gguf_ctx, "general.quantization_version");
         if (q_ver_idx != -1) {
-            hparams.ftype = gguf_get_val_u32(gguf_ctx, q_ver_idx);
+            hparams.ftype = (enum llama_ftype) gguf_get_val_u32(gguf_ctx, q_ver_idx);
         }
 
         hparams.n_vocab = read_n_vocab();