Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	examples/model-conversion/Makefile
#	examples/model-conversion/scripts/causal/convert-model.sh
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	scripts/compare-commits.sh
This commit is contained in:
Concedo
2025-08-28 23:17:29 +08:00
parent 0f2436b320 73804145ab
commit 3060dfb99f
28 changed files with 399 additions and 261 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-adapter.cpp
+68 -4
View File
@@ -163,13 +163,38 @@ static void llama_adapter_lora_init_impl(llama_model & model, const char * path_
// check metadata
{
const gguf_context * gguf_ctx = ctx_gguf.get();
LLAMA_LOG_INFO("%s: Dumping metadata keys/values.\n", __func__);
// get metadata as string
for (int i = 0; i < gguf_get_n_kv(gguf_ctx); i++) {
gguf_type type = gguf_get_kv_type(gguf_ctx, i);
const std::string type_name =
type == GGUF_TYPE_ARRAY
? format("%s[%s,%zu]", gguf_type_name(type), gguf_type_name(gguf_get_arr_type(gguf_ctx, i)), gguf_get_arr_n(gguf_ctx, i))
: gguf_type_name(type);
const char * name = gguf_get_key(gguf_ctx, i);
const std::string value = gguf_kv_to_str(gguf_ctx, i);
if (type != GGUF_TYPE_ARRAY) {
adapter.gguf_kv.emplace(name, value);
}
const size_t MAX_VALUE_LEN = 40;
std::string print_value = value.size() > MAX_VALUE_LEN ? format("%s...", value.substr(0, MAX_VALUE_LEN - 3).c_str()) : value;
replace_all(print_value, "\n", "\\n");
LLAMA_LOG_INFO("%s: - kv %3d: %42s %-16s = %s\n", __func__, i, name, type_name.c_str(), print_value.c_str());
}
auto get_kv_str = [&](const std::string & key) -> std::string {
int id = gguf_find_key(ctx_gguf.get(), key.c_str());
return id < 0 ? "" : std::string(gguf_get_val_str(ctx_gguf.get(), id));
int id = gguf_find_key(gguf_ctx, key.c_str());
return id < 0 ? "" : std::string(gguf_get_val_str(gguf_ctx, id));
};
auto get_kv_f32 = [&](const std::string & key) -> float {
int id = gguf_find_key(ctx_gguf.get(), key.c_str());
return id < 0 ? 0.0f : gguf_get_val_f32(ctx_gguf.get(), id);
int id = gguf_find_key(gguf_ctx, key.c_str());
return id < 0 ? 0.0f : gguf_get_val_f32(gguf_ctx, id);
};
LLM_KV llm_kv = LLM_KV(LLM_ARCH_UNKNOWN);
@@ -383,6 +408,45 @@ llama_adapter_lora * llama_adapter_lora_init(llama_model * model, const char * p
return nullptr;
}
int32_t llama_adapter_meta_val_str(const llama_adapter_lora * adapter, const char * key, char * buf, size_t buf_size) {
const auto & it = adapter->gguf_kv.find(key);
if (it == adapter->gguf_kv.end()) {
if (buf_size > 0) {
buf[0] = '\0';
}
return -1;
}
return snprintf(buf, buf_size, "%s", it->second.c_str());
}
int32_t llama_adapter_meta_count(const llama_adapter_lora * adapter) {
return (int)adapter->gguf_kv.size();
}
int32_t llama_adapter_meta_key_by_index(const llama_adapter_lora * adapter, int i, char * buf, size_t buf_size) {
if (i < 0 || i >= (int)adapter->gguf_kv.size()) {
if (buf_size > 0) {
buf[0] = '\0';
}
return -1;
}
auto it = adapter->gguf_kv.begin();
std::advance(it, i);
return snprintf(buf, buf_size, "%s", it->first.c_str());
}
int32_t llama_adapter_meta_val_str_by_index(const llama_adapter_lora * adapter, int32_t i, char * buf, size_t buf_size) {
if (i < 0 || i >= (int)adapter->gguf_kv.size()) {
if (buf_size > 0) {
buf[0] = '\0';
}
return -1;
}
auto it = adapter->gguf_kv.begin();
std::advance(it, i);
return snprintf(buf, buf_size, "%s", it->second.c_str());
}
void llama_adapter_lora_free(llama_adapter_lora * adapter) {
delete adapter;
}
src/llama-adapter.h
+3
View File
@@ -67,6 +67,9 @@ struct llama_adapter_lora {
float alpha;
// gguf metadata
std::unordered_map<std::string, std::string> gguf_kv;
llama_adapter_lora() = default;
~llama_adapter_lora() = default;
src/llama-arch.cpp
+19 -2
View File
@@ -22,6 +22,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
{ LLM_ARCH_NOMIC_BERT_MOE, "nomic-bert-moe" },
{ LLM_ARCH_NEO_BERT, "neo-bert" },
{ LLM_ARCH_JINA_BERT_V2, "jina-bert-v2" },
{ LLM_ARCH_JINA_BERT_V3, "jina-bert-v3" },
{ LLM_ARCH_BLOOM, "bloom" },
{ LLM_ARCH_STABLELM, "stablelm" },
{ LLM_ARCH_QWEN, "qwen" },
@@ -234,8 +235,10 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
{ LLM_KV_TOKENIZER_FIM_REP_ID, "tokenizer.ggml.fim_rep_token_id" },
{ LLM_KV_TOKENIZER_FIM_SEP_ID, "tokenizer.ggml.fim_sep_token_id" },
{ LLM_KV_ADAPTER_TYPE, "adapter.type" },
{ LLM_KV_ADAPTER_LORA_ALPHA, "adapter.lora.alpha" },
{ LLM_KV_ADAPTER_TYPE, "adapter.type" },
{ LLM_KV_ADAPTER_LORA_ALPHA, "adapter.lora.alpha" },
{ LLM_KV_ADAPTER_LORA_TASK_NAME, "adapter.lora.task_name" },
{ LLM_KV_ADAPTER_LORA_PROMPT_PREFIX, "adapter.lora.prompt_prefix" },
// deprecated
{ LLM_KV_TOKENIZER_PREFIX_ID, "tokenizer.ggml.prefix_token_id" },
@@ -575,6 +578,20 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
{ LLM_TENSOR_CLS, "cls" },
},
},
{
LLM_ARCH_JINA_BERT_V3,
{
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_TOKEN_EMBD_NORM, "token_embd_norm" },
{ LLM_TENSOR_TOKEN_TYPES, "token_types" },
{ LLM_TENSOR_ATTN_OUT_NORM, "blk.%d.attn_output_norm" },
{ LLM_TENSOR_ATTN_QKV, "blk.%d.attn_qkv" },
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
{ LLM_TENSOR_LAYER_OUT_NORM, "blk.%d.layer_output_norm" },
},
},
{
LLM_ARCH_BLOOM,
{
src/llama-arch.h
+3
View File
@@ -26,6 +26,7 @@ enum llm_arch {
LLM_ARCH_NOMIC_BERT_MOE,
LLM_ARCH_NEO_BERT,
LLM_ARCH_JINA_BERT_V2,
LLM_ARCH_JINA_BERT_V3,
LLM_ARCH_BLOOM,
LLM_ARCH_STABLELM,
LLM_ARCH_QWEN,
@@ -230,6 +231,8 @@ enum llm_kv {
LLM_KV_ADAPTER_TYPE,
LLM_KV_ADAPTER_LORA_ALPHA,
LLM_KV_ADAPTER_LORA_TASK_NAME,
LLM_KV_ADAPTER_LORA_PROMPT_PREFIX,
LLM_KV_POSNET_EMBEDDING_LENGTH,
LLM_KV_POSNET_BLOCK_COUNT,
src/llama-context.cpp
-22
View File
@@ -102,16 +102,6 @@ llama_context::llama_context(
cparams.op_offload = params.op_offload;
cparams.kv_unified = params.kv_unified;
{
const char * LLAMA_SET_ROWS = getenv("LLAMA_SET_ROWS");
supports_set_rows = LLAMA_SET_ROWS ? (atoi(LLAMA_SET_ROWS) != 0) : supports_set_rows;
if (!supports_set_rows && !cparams.kv_unified) {
LLAMA_LOG_WARN("%s: non-unified KV cache requires ggml_set_rows() - forcing unified KV cache\n", __func__);
cparams.kv_unified = true;
}
}
{
const char * LLAMA_GRAPH_REUSE_DISABLE = getenv("LLAMA_GRAPH_REUSE_DISABLE");
graph_reuse_disable = LLAMA_GRAPH_REUSE_DISABLE ? (atoi(LLAMA_GRAPH_REUSE_DISABLE) != 0) : graph_reuse_disable;
@@ -890,12 +880,6 @@ int llama_context::encode(const llama_batch & batch_inp) {
}
}
if (!supports_set_rows) {
// Reset state for the next token before backend sync, to allow the CPU activities in the reset to
// overlap with device computation.
ggml_backend_sched_reset(sched.get());
}
// TODO: hacky solution
if (model.arch == LLM_ARCH_T5 && t_embd) {
//cross.t_embd = t_embd;
@@ -1226,12 +1210,6 @@ int llama_context::decode(const llama_batch & batch_inp) {
// wait for the computation to finish (automatically done when obtaining the model output)
//synchronize();
if (!supports_set_rows) {
// Reset state for the next token before backend sync, to allow the CPU activities in the reset to
// overlap with device computation.
ggml_backend_sched_reset(sched.get());
}
return 0;
}
src/llama-context.h
-4
View File
@@ -283,10 +283,6 @@ private:
bool has_evaluated_once = false;
// env: LLAMA_SET_ROWS (temporary)
// ref: https://github.com/ggml-org/llama.cpp/pull/14285
bool supports_set_rows = true;
// env: LLAMA_GRAPH_REUSE_DISABLE
bool graph_reuse_disable = false;
src/llama-graph.cpp
-4
View File
@@ -314,8 +314,6 @@ bool llm_graph_input_attn_kv::can_reuse(const llm_graph_params & params) {
res &= self_kq_mask->ne[0] == mctx->get_n_kv();
res &= self_kq_mask->ne[1] == GGML_PAD(params.ubatch.n_tokens, GGML_KQ_MASK_PAD);
res &= mctx->get_supports_set_rows(); // TODO: tmp
return res;
}
@@ -350,8 +348,6 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) {
res &= self_kq_mask_swa->ne[0] == mctx->get_swa()->get_n_kv();
res &= self_kq_mask_swa->ne[1] == GGML_PAD(params.ubatch.n_tokens, GGML_KQ_MASK_PAD);
res &= mctx->get_base()->get_supports_set_rows(); // TODO: tmp
return res;
}
src/llama-kv-cache.cpp
+35 -100
View File
@@ -197,18 +197,6 @@ llama_kv_cache::llama_kv_cache(
const char * LLAMA_KV_CACHE_DEBUG = getenv("LLAMA_KV_CACHE_DEBUG");
debug = LLAMA_KV_CACHE_DEBUG ? atoi(LLAMA_KV_CACHE_DEBUG) : 0;
const char * LLAMA_SET_ROWS = getenv("LLAMA_SET_ROWS");
supports_set_rows = LLAMA_SET_ROWS ? atoi(LLAMA_SET_ROWS) != 0 : supports_set_rows;
if (!supports_set_rows) {
// ref: https://github.com/ggml-org/llama.cpp/pull/14363
GGML_ASSERT(unified && "cannot use non-unified KV cache without ggml_set_rows() support");
}
if (!supports_set_rows) {
LLAMA_LOG_WARN("%s: LLAMA_SET_ROWS=0, using old ggml_cpy() method for backwards compatibility\n", __func__);
}
}
void llama_kv_cache::clear(bool data) {
@@ -551,11 +539,8 @@ llama_kv_cache::slot_info_vec_t llama_kv_cache::prepare(const std::vector<llama_
bool success = true;
for (const auto & ubatch : ubatches) {
// non-continuous slots require support for ggml_set_rows()
const bool cont = supports_set_rows ? false : true;
// only find a suitable slot for the ubatch. don't modify the cells yet
const auto sinfo_new = find_slot(ubatch, cont);
const auto sinfo_new = find_slot(ubatch, false);
if (sinfo_new.empty()) {
success = false;
break;
@@ -771,8 +756,8 @@ llama_kv_cache::slot_info llama_kv_cache::find_slot(const llama_ubatch & ubatch,
GGML_ASSERT(ubatch.seq_id [s*n_tokens][0] == seq_id);
}
res.s0 = std::min<llama_seq_id>(res.s0, seq_to_stream[seq_id]);
res.s1 = std::max<llama_seq_id>(res.s1, seq_to_stream[seq_id]);
res.s0 = std::min<uint32_t>(res.s0, seq_to_stream[seq_id]);
res.s1 = std::max<uint32_t>(res.s1, seq_to_stream[seq_id]);
res.strm[s] = seq_to_stream[seq_id];
res.idxs[s].reserve(n_tokens);
@@ -964,11 +949,11 @@ bool llama_kv_cache::get_has_shift() const {
return result;
}
uint32_t llama_kv_cache::get_n_kv() const {
uint32_t llama_kv_cache::get_n_kv(const slot_info & sinfo) const {
uint32_t result = 0;
for (uint32_t s = 0; s < n_stream; ++s) {
const auto & cells = v_cells[s];
for (uint32_t s = 0; s < sinfo.n_stream(); ++s) {
const auto & cells = v_cells[sinfo.strm[s]];
result = std::max(std::min(cells.size(), std::max(n_pad, GGML_PAD(cells.used_max_p1(), n_pad))), result);
}
@@ -976,10 +961,6 @@ uint32_t llama_kv_cache::get_n_kv() const {
return result;
}
bool llama_kv_cache::get_supports_set_rows() const {
return supports_set_rows;
}
ggml_tensor * llama_kv_cache::get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const {
const int32_t ikv = map_layer_ids.at(il);
@@ -1017,52 +998,42 @@ ggml_tensor * llama_kv_cache::get_v(ggml_context * ctx, int32_t il, uint32_t n_k
// note: v->nb[1] <= v->nb[2]
return ggml_view_4d(ctx, v,
hparams.n_embd_head_v, hparams.n_head_kv(il), n_kv, ns,
ggml_row_size(v->type, hparams.n_embd_head_v), // v->nb[1]
ggml_row_size(v->type, n_embd_v_gqa), // v->nb[2]
ggml_row_size(v->type, n_embd_v_gqa*kv_size), // v->nb[3]
ggml_row_size(v->type, hparams.n_embd_head_v), // v->nb[1]
ggml_row_size(v->type, n_embd_v_gqa), // v->nb[2]
ggml_row_size(v->type, n_embd_v_gqa*kv_size), // v->nb[3]
ggml_row_size(v->type, n_embd_v_gqa*kv_size)*sinfo.s0);
}
// note: v->nb[1] > v->nb[2]
return ggml_view_4d(ctx, v,
n_kv, hparams.n_head_kv(il), hparams.n_embd_head_v, ns,
ggml_row_size(v->type, kv_size*hparams.n_embd_head_v), // v->nb[1]
ggml_row_size(v->type, kv_size), // v->nb[2]
ggml_row_size(v->type, kv_size*n_embd_v_gqa), // v->nb[3]
ggml_row_size(v->type, kv_size*hparams.n_embd_head_v), // v->nb[1]
ggml_row_size(v->type, kv_size), // v->nb[2]
ggml_row_size(v->type, kv_size*n_embd_v_gqa), // v->nb[3]
ggml_row_size(v->type, kv_size*n_embd_v_gqa)*sinfo.s0);
}
ggml_tensor * llama_kv_cache::cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const {
GGML_UNUSED(sinfo);
const int32_t ikv = map_layer_ids.at(il);
auto * k = layers[ikv].k;
const int64_t n_embd_k_gqa = k->ne[0];
const int64_t n_tokens = k_cur->ne[2];
k_cur = ggml_reshape_2d(ctx, k_cur, k->ne[0], n_tokens);
if (k_idxs && supports_set_rows) {
if (k->ne[2] > 1) {
k = ggml_reshape_2d(ctx, k, k->ne[0], k->ne[1]*k->ne[2]);
}
return ggml_set_rows(ctx, k, k_cur, k_idxs);
if (k->ne[2] > 1) {
k = ggml_reshape_2d(ctx, k, k->ne[0], k->ne[1]*k->ne[2]);
}
// TODO: fallback to old ggml_cpy() method for backwards compatibility
// will be removed when ggml_set_rows() is adopted by all backends
GGML_ASSERT(n_stream == 1 && "n_stream > 1 not supported without LLAMA_SET_ROWS");
ggml_tensor * k_view = ggml_view_1d(ctx, k,
n_tokens*n_embd_k_gqa,
ggml_row_size(k->type, n_embd_k_gqa)*sinfo.head());
return ggml_cpy(ctx, k_cur, k_view);
return ggml_set_rows(ctx, k, k_cur, k_idxs);
}
ggml_tensor * llama_kv_cache::cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggml_tensor * v_idxs, int32_t il, const slot_info & sinfo) const {
GGML_UNUSED(sinfo);
const int32_t ikv = map_layer_ids.at(il);
auto * v = layers[ikv].v;
@@ -1072,48 +1043,25 @@ ggml_tensor * llama_kv_cache::cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggm
v_cur = ggml_reshape_2d(ctx, v_cur, n_embd_v_gqa, n_tokens);
if (v_idxs && supports_set_rows) {
if (!v_trans) {
if (v->ne[2] > 1) {
v = ggml_reshape_2d(ctx, v, v->ne[0], v->ne[1]*v->ne[2]);
}
return ggml_set_rows(ctx, v, v_cur, v_idxs);
}
// [TAG_V_CACHE_VARIABLE]
if (n_embd_v_gqa < v->ne[0]) {
v_cur = ggml_pad(ctx, v_cur, v->ne[0] - n_embd_v_gqa, 0, 0, 0);
}
// the row becomes a single element
ggml_tensor * v_view = ggml_reshape_2d(ctx, v, 1, v->ne[0]*v->ne[1]*v->ne[2]);
v_cur = ggml_reshape_2d(ctx, v_cur, 1, v_cur->ne[0]*v_cur->ne[1]);
return ggml_set_rows(ctx, v_view, v_cur, v_idxs);
}
// TODO: fallback to old ggml_cpy() method for backwards compatibility
// will be removed when ggml_set_rows() is adopted by all backends
GGML_ASSERT(n_stream == 1 && "n_stream > 1 not supported without LLAMA_SET_ROWS");
ggml_tensor * v_view = nullptr;
if (!v_trans) {
v_view = ggml_view_1d(ctx, v,
n_tokens*n_embd_v_gqa,
ggml_row_size(v->type, n_embd_v_gqa)*sinfo.head());
} else {
v_cur = ggml_transpose(ctx, v_cur);
if (v->ne[2] > 1) {
v = ggml_reshape_2d(ctx, v, v->ne[0], v->ne[1]*v->ne[2]);
}
v_view = ggml_view_2d(ctx, v, n_tokens, n_embd_v_gqa,
(v->ne[1] )*ggml_element_size(v),
(sinfo.head())*ggml_element_size(v));
return ggml_set_rows(ctx, v, v_cur, v_idxs);
}
return ggml_cpy(ctx, v_cur, v_view);
// [TAG_V_CACHE_VARIABLE]
if (n_embd_v_gqa < v->ne[0]) {
v_cur = ggml_pad(ctx, v_cur, v->ne[0] - n_embd_v_gqa, 0, 0, 0);
}
// the row becomes a single element
ggml_tensor * v_view = ggml_reshape_2d(ctx, v, 1, v->ne[0]*v->ne[1]*v->ne[2]);
v_cur = ggml_reshape_2d(ctx, v_cur, 1, v_cur->ne[0]*v_cur->ne[1]);
return ggml_set_rows(ctx, v_view, v_cur, v_idxs);
}
ggml_tensor * llama_kv_cache::build_input_k_idxs(ggml_context * ctx, const llama_ubatch & ubatch) const {
@@ -1143,10 +1091,6 @@ ggml_tensor * llama_kv_cache::build_input_v_idxs(ggml_context * ctx, const llama
}
void llama_kv_cache::set_input_k_idxs(ggml_tensor * dst, const llama_ubatch * ubatch, const slot_info & sinfo) const {
if (!supports_set_rows) {
return;
}
const uint32_t n_tokens = ubatch->n_tokens;
GGML_ASSERT(n_tokens == (int64_t) sinfo.size()*sinfo.n_stream());
@@ -1163,10 +1107,6 @@ void llama_kv_cache::set_input_k_idxs(ggml_tensor * dst, const llama_ubatch * ub
}
void llama_kv_cache::set_input_v_idxs(ggml_tensor * dst, const llama_ubatch * ubatch, const slot_info & sinfo) const {
if (!supports_set_rows) {
return;
}
const uint32_t n_tokens = ubatch->n_tokens;
GGML_ASSERT(n_tokens == (int64_t) sinfo.size()*sinfo.n_stream());
@@ -1985,8 +1925,7 @@ bool llama_kv_cache_context::apply() {
}
kv->apply_ubatch(sinfos[i_cur], ubatches[i_cur]);
n_kv = kv->get_n_kv();
n_kv = kv->get_n_kv(sinfos[i_cur]);
return true;
}
@@ -2005,10 +1944,6 @@ uint32_t llama_kv_cache_context::get_n_kv() const {
return n_kv;
}
bool llama_kv_cache_context::get_supports_set_rows() const {
return kv->get_supports_set_rows();
}
ggml_tensor * llama_kv_cache_context::get_k(ggml_context * ctx, int32_t il) const {
return kv->get_k(ctx, il, n_kv, sinfos[i_cur]);
}
src/llama-kv-cache.h
+3 -13
View File
@@ -38,8 +38,8 @@ public:
using idx_vec_t = std::vector<uint32_t>;
// number of streams: ns = s1 - s0 + 1
llama_seq_id s0;
llama_seq_id s1;
uint32_t s0;
uint32_t s1;
std::vector<llama_seq_id> strm; // [ns]
std::vector<idx_vec_t> idxs; // [ns]
@@ -139,10 +139,7 @@ public:
// graph_build API
//
uint32_t get_n_kv() const;
// TODO: temporary
bool get_supports_set_rows() const;
uint32_t get_n_kv(const slot_info & sinfo) const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const;
@@ -215,10 +212,6 @@ private:
// env: LLAMA_KV_CACHE_DEBUG
int debug = 0;
// env: LLAMA_SET_ROWS (temporary)
// ref: https://github.com/ggml-org/llama.cpp/pull/14285
bool supports_set_rows = true;
const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE;
std::vector<ggml_context_ptr> ctxs;
@@ -318,9 +311,6 @@ public:
uint32_t get_n_kv() const;
// TODO: temporary
bool get_supports_set_rows() const;
// get views of the current state of the cache
ggml_tensor * get_k(ggml_context * ctx, int32_t il) const;
ggml_tensor * get_v(ggml_context * ctx, int32_t il) const;
src/llama-model.cpp
+25 -10
View File
@@ -52,6 +52,7 @@ const char * llm_type_name(llm_type type) {
case LLM_TYPE_410M: return "410M";
case LLM_TYPE_450M: return "450M";
case LLM_TYPE_475M: return "475M";
case LLM_TYPE_558M: return "558M";
case LLM_TYPE_700M: return "700M";
case LLM_TYPE_770M: return "770M";
case LLM_TYPE_780M: return "780M";
@@ -777,6 +778,18 @@ void llama_model::load_hparams(llama_model_loader & ml) {
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_JINA_BERT_V3:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_EPS, hparams.f_norm_eps);
ml.get_key(LLM_KV_ATTENTION_CAUSAL, hparams.causal_attn);
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
switch (hparams.n_layer) {
case 24:
type = LLM_TYPE_558M; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
{
@@ -2727,6 +2740,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
case LLM_ARCH_BERT:
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
case LLM_ARCH_JINA_BERT_V3:
{
tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
type_embd = create_tensor(tn(LLM_TENSOR_TOKEN_TYPES, "weight"), {n_embd, n_token_types}, TENSOR_NOT_REQUIRED);
@@ -2762,24 +2776,22 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
}
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, TENSOR_NOT_REQUIRED);
layer.attn_out_norm = create_tensor(tn(LLM_TENSOR_ATTN_OUT_NORM, "weight", i), {n_embd}, 0);
layer.attn_out_norm_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT_NORM, "bias", i), {n_embd}, 0);
if (hparams.moe_every_n_layers > 0 && i % hparams.moe_every_n_layers == 1) {
layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, 0);
layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), { n_embd, n_ff, n_expert}, 0);
layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), { n_ff, n_embd, n_expert}, 0);
layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0);
} else {
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0);
layer.ffn_up_b = create_tensor(tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, TENSOR_NOT_REQUIRED);
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), {n_ff, n_embd}, 0);
layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, TENSOR_NOT_REQUIRED);
if (arch == LLM_ARCH_BERT || arch == LLM_ARCH_NOMIC_BERT_MOE) {
layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd}, 0);
layer.ffn_up_b = create_tensor(tn(LLM_TENSOR_FFN_UP, "bias", i), {n_ff}, 0);
layer.ffn_down_b = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "bias", i), {n_embd}, 0);
} else {
if (arch == LLM_ARCH_NOMIC_BERT) {
layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
}
}
@@ -7561,7 +7573,7 @@ struct llm_build_bert : public llm_graph_context {
}
// RoPE
if (model.arch == LLM_ARCH_NOMIC_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE) {
if (model.arch == LLM_ARCH_NOMIC_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE || model.arch == LLM_ARCH_JINA_BERT_V3) {
Qcur = ggml_rope_ext(
ctx0, Qcur, inp_pos, nullptr,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
@@ -7620,7 +7632,7 @@ struct llm_build_bert : public llm_graph_context {
0.0f,
LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX, il);
cb(cur, "ffn_moe_out", il);
} else if (model.arch == LLM_ARCH_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE) {
} else if (model.arch == LLM_ARCH_BERT || model.arch == LLM_ARCH_NOMIC_BERT_MOE || model.arch == LLM_ARCH_JINA_BERT_V3) {
cur = build_ffn(cur,
model.layers[il].ffn_up, model.layers[il].ffn_up_b, NULL,
NULL, NULL, NULL,
@@ -18341,6 +18353,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params,
// switch statement
case LLM_ARCH_BERT:
case LLM_ARCH_JINA_BERT_V2:
case LLM_ARCH_JINA_BERT_V3:
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
case LLM_ARCH_NEO_BERT:
@@ -18495,6 +18508,7 @@ ggml_cgraph * llama_model::build_graph(const llm_graph_params & params) const {
} break;
case LLM_ARCH_BERT:
case LLM_ARCH_JINA_BERT_V2:
case LLM_ARCH_JINA_BERT_V3:
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
{
@@ -18985,6 +18999,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
case LLM_ARCH_GROK:
case LLM_ARCH_DBRX:
case LLM_ARCH_BERT:
case LLM_ARCH_JINA_BERT_V3:
case LLM_ARCH_NOMIC_BERT:
case LLM_ARCH_NOMIC_BERT_MOE:
case LLM_ARCH_STABLELM:
src/llama-model.h
+1
View File
@@ -40,6 +40,7 @@ enum llm_type {
LLM_TYPE_450M,
LLM_TYPE_475M,
LLM_TYPE_537M,
LLM_TYPE_558M,
LLM_TYPE_700M,
LLM_TYPE_770M,
LLM_TYPE_780M,
src/llama-vocab.cpp
+1 -1
View File
@@ -2709,7 +2709,7 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
// set attributes by model/tokenizer/architecture name
if (false
|| _contains_any(tokenizer_pre, {"jina-v2-de", "jina-v2-es", "jina-v2-code"})
|| _contains_any(general_arch, {"nomic-bert-moe"})
|| _contains_any(general_arch, {"nomic-bert-moe", "jina-bert-v3"})
) {
if (token_to_id.count("<mask>") == 0) {
LLAMA_LOG_WARN("%s: Mask token is missing in vocab, please reconvert model!\n", __func__);