feat: whitelist jina bert v2 for llama-server embedding

ggerganov · Aug 12, 2024 · afa6800 · afa6800
1 parent 4134999
commit afa6800
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/examples/server/server.cpp b/examples/server/server.cpp
@@ -693,7 +693,10 @@ struct server_context {
         n_ctx = llama_n_ctx(ctx);
 
         add_bos_token = llama_should_add_bos_token(model);
-        GGML_ASSERT(llama_add_eos_token(model) != 1);
+
+        if (!llama_model_has_encoder(model)) {
+            GGML_ASSERT(llama_add_eos_token(model) != 1);
+        }
 
         return true;
     }

diff --git a/src/llama.cpp b/src/llama.cpp
@@ -17190,6 +17190,7 @@ bool llama_model_has_encoder(const struct llama_model * model) {
     switch (model->arch) {
         case LLM_ARCH_T5:        return true;
         case LLM_ARCH_T5ENCODER: return true;
+        case LLM_ARCH_JINA_BERT_V2: return true;
         default:                 return false;
     }
 }