matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama: fix kv loading on snowflake-arctic-embed models (#9536)

Browse Source
This commit is contained in:
Jeffrey Morgan
2025-03-07 09:25:34 -08:00
committed by GitHub
parent a7e63b82be
commit 4289c74359
4 changed files with 71 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ml/backend/ggml/ggml/include/gguf.h vendored
View File

@@ -114,6 +114,7 @@ extern "C" {
// get raw pointer to the first element of the array with the given key_id
// for bool arrays, note that they are always stored as int8 on all platforms (usually this makes no difference)
GGML_API const void * gguf_get_arr_data(const struct gguf_context * ctx, int64_t key_id);
GGML_API size_t gguf_get_arr_data_n(const struct gguf_context * ctx, int64_t key_id);
// get ith C string from array with given key_id
GGML_API const char * gguf_get_arr_str (const struct gguf_context * ctx, int64_t key_id, size_t i);

7
ml/backend/ggml/ggml/src/gguf.cpp vendored
View File

@@ -777,10 +777,14 @@ enum gguf_type gguf_get_arr_type(const struct gguf_context * ctx, int64_t key_id
const void * gguf_get_arr_data(const struct gguf_context * ctx, int64_t key_id) {
GGML_ASSERT(key_id >= 0 && key_id < gguf_get_n_kv(ctx));
GGML_ASSERT(ctx->kv[key_id].get_type() != GGUF_TYPE_STRING);
return ctx->kv[key_id].data.data();
}
size_t gguf_get_arr_data_n(const struct gguf_context * ctx, int64_t key_id) {
GGML_ASSERT(key_id >= 0 && key_id < gguf_get_n_kv(ctx));
return ctx->kv[key_id].data.size();
}
const char * gguf_get_arr_str(const struct gguf_context * ctx, int64_t key_id, size_t i) {
GGML_ASSERT(key_id >= 0 && key_id < gguf_get_n_kv(ctx));
GGML_ASSERT(ctx->kv[key_id].get_type() == GGUF_TYPE_STRING);
@@ -874,7 +878,6 @@ const char * gguf_get_val_str(const struct gguf_context * ctx, int64_t key_id) {
const void * gguf_get_val_data(const struct gguf_context * ctx, int64_t key_id) {
GGML_ASSERT(key_id >= 0 && key_id < gguf_get_n_kv(ctx));
GGML_ASSERT(ctx->kv[key_id].get_ne() == 1);
GGML_ASSERT(ctx->kv[key_id].get_type() != GGUF_TYPE_STRING);
return ctx->kv[key_id].data.data();
}