model : add NeoBERT (ggml-org#14164)

* convert neobert model to gguf

* add inference graph

* fix flake8 lint

* followed reviewer suggestions

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* follow reviewers suggestions

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* override NeoBERT feed-forward length

---------

Co-authored-by: dinhhuy <huy.dinh@brains-tech.co.jp>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

Author: 3 people

src/llama-model.cpp

@@ -6319,57 +6319,56 @@ struct llm_build_neo_bert : public llm_graph_context {
 
         auto * inp_attn = build_attn_inp_no_cache();
 
-        ggml_tensor * inp_out_ids = build_inp_out_ids();
-
+        // iterate layers
         for (int il = 0; il < n_layer; ++il) {
             ggml_tensor * cur = inpL;
 
+            ggml_tensor * Qcur;
+            ggml_tensor * Kcur;
+            ggml_tensor * Vcur;
+
             // pre-norm
             cur = build_norm(inpL,
                     model.layers[il].attn_norm, NULL,
                     LLM_NORM_RMS, il);
 
-            {
-                ggml_tensor * Qcur;
-                ggml_tensor * Kcur;
-                ggml_tensor * Vcur;
-
-                // self-attention
-                cur = build_lora_mm(model.layers[il].wqkv, cur);
-                cb(cur, "wqkv", il);
-
-                Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd,     n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
-                Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
-                Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
-
-                Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
-                Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
-                Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
-
-                // RoPE
-                Qcur = ggml_rope_ext(
-                        ctx0, Qcur, inp_pos, nullptr,
-                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
-                        ext_factor, attn_factor, beta_fast, beta_slow
-                        );
+            // self-attention
+            cur = build_lora_mm(model.layers[il].wqkv, cur);
+            cb(cur, "wqkv", il);
+
+            Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd,     n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
+            Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
+            Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));
+
+            Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
+            Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
+            Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);
+
+            // RoPE
+            Qcur = ggml_rope_ext(
+                    ctx0, Qcur, inp_pos, nullptr,
+                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                    ext_factor, attn_factor, beta_fast, beta_slow
+                    );
 
-                Kcur = ggml_rope_ext(
-                        ctx0, Kcur, inp_pos, nullptr,
-                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
-                        ext_factor, attn_factor, beta_fast, beta_slow
-                        );
+            Kcur = ggml_rope_ext(
+                    ctx0, Kcur, inp_pos, nullptr,
+                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
+                    ext_factor, attn_factor, beta_fast, beta_slow
+                    );
 
-                cb(Qcur, "Qcur", il);
-                cb(Kcur, "Kcur", il);
-                cb(Vcur, "Vcur", il);
+            cb(Qcur, "Qcur", il);
+            cb(Kcur, "Kcur", il);
+            cb(Vcur, "Vcur", il);
 
-                cur = build_attn(inp_attn, gf,
-                        model.layers[il].wo, nullptr,
-                        Qcur, Kcur, Vcur, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
-                cb(cur, "kqv_out", il);
-            }
+            cur = build_attn(inp_attn, gf,
+                    model.layers[il].wo, nullptr,
+                    Qcur, Kcur, Vcur, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);
+            cb(cur, "kqv_out", il);
 
-            if (il == n_layer - 1 && inp_out_ids) {
+            if (il == n_layer - 1 && pooling_type == LLAMA_POOLING_TYPE_NONE) {
+                // skip computing output for unused tokens
+                ggml_tensor * inp_out_ids = build_inp_out_ids();
                 cur  = ggml_get_rows(ctx0,  cur, inp_out_ids);
                 inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
             }
@@ -14798,6 +14797,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
         case LLM_ARCH_GRANITE_MOE:
         case LLM_ARCH_CHAMELEON:
         case LLM_ARCH_BAILINGMOE:
+        case LLM_ARCH_NEO_BERT:
         case LLM_ARCH_ARCEE:
             return LLAMA_ROPE_TYPE_NORM;