talk-llama : sync llama.cpp

ggml-ci
2025-06-15 05:18:07 +00:00 · 2025-06-01 14:07:36 +03:00
parent 3f46282cbe
commit 7fd6fa8097
22 changed files with 4265 additions and 3552 deletions
--- a/examples/talk-llama/llama-arch.cpp
+++ b/examples/talk-llama/llama-arch.cpp
@ -174,6 +174,8 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
    { LLM_KV_CONVNEXT_EMBEDDING_LENGTH, "%s.convnext.embedding_length" },
    { LLM_KV_CONVNEXT_BLOCK_COUNT,      "%s.convnext.block_count"      },

+    { LLM_KV_CLASSIFIER_OUTPUT_LABELS, "%s.classifier.output_labels" },
+
    { LLM_KV_TOKENIZER_MODEL,                "tokenizer.ggml.model"                    },
    { LLM_KV_TOKENIZER_PRE,                  "tokenizer.ggml.pre"                      },
    { LLM_KV_TOKENIZER_LIST,                 "tokenizer.ggml.tokens"                   },
@ -448,6 +450,7 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
            { LLM_TENSOR_TOKEN_TYPES,     "token_types" },
            { LLM_TENSOR_POS_EMBD,        "position_embd" },
            { LLM_TENSOR_ATTN_OUT_NORM,   "blk.%d.attn_output_norm" },
+            { LLM_TENSOR_ATTN_QKV,        "blk.%d.attn_qkv" },
            { LLM_TENSOR_ATTN_Q,          "blk.%d.attn_q" },
            { LLM_TENSOR_ATTN_K,          "blk.%d.attn_k" },
            { LLM_TENSOR_ATTN_V,          "blk.%d.attn_v" },