model : add label for LiquidAI LFM2-2.6B model (#16204)

* model : add label for LiquidAI LFM2-2.6B model

HF link: [LiquidAI/LFM2-2.6B](https://huggingface.co/LiquidAI/LFM2-2.6B).

Support for GGUF conversion and inference is added in #14620.

However, due to similar `n_embd`, it identifies as a 1.2B model.
Fix the label by using `n_ff` to identify the model instead.

Output of `llama-bench`:
```
| model                          |       size |     params | backend    | threads |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | --------------: | -------------------: |
| lfm2 1.2B F16                  |   2.18 GiB |     1.17 B | CPU        |      10 |           pp512 |        223.97 ± 5.32 |
| lfm2 2.6B F16                  |   4.79 GiB |     2.57 B | CPU        |      10 |           pp512 |         92.53 ± 4.14 |
| lfm2 350M F16                  | 676.25 MiB |   354.48 M | CPU        |      10 |           pp512 |       725.52 ± 11.70 |
| lfm2 700M F16                  |   1.38 GiB |   742.49 M | CPU        |      10 |           pp512 |       336.22 ± 12.93 |
```

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <redacted>
---------

Co-authored-by: Sigbjørn Skjæret <redacted>

diff --git a/src/llama-model.cpp b/src/llama-model.cpp
index 981e57083c48d90610fd413496e90e14d858ad7f..396567742d87e6c7b016cc07bb5fb3960f405efb 100644 (file)
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -66,6 +66,7 @@ const char * llm_type_name(llm_type type) {
         case LLM_TYPE_1_7B:          return "1.7B";
         case LLM_TYPE_1_8B:          return "1.8B";
         case LLM_TYPE_2B:            return "2B";
+        case LLM_TYPE_2_6B:          return "2.6B";
         case LLM_TYPE_2_8B:          return "2.8B";
         case LLM_TYPE_2_9B:          return "2.9B";
         case LLM_TYPE_3B:            return "3B";
@@ -1977,10 +1978,11 @@ void llama_model::load_hparams(llama_model_loader & ml) {
                 for (uint32_t il = 0; il < hparams.n_layer; ++il) {
                     hparams.recurrent_layer_arr[il] = hparams.n_head_kv(il) == 0;
                 }
-                switch (hparams.n_embd) {
-                    case 1024: type = LLM_TYPE_350M; break;
-                    case 1536: type = LLM_TYPE_700M; break;
-                    case 2048: type = LLM_TYPE_1_2B; break;
+                switch (hparams.n_ff()) {
+                    case  4608: type = LLM_TYPE_350M; break;
+                    case  6912: type = LLM_TYPE_700M; break;
+                    case  8192: type = LLM_TYPE_1_2B; break;
+                    case 10752: type = LLM_TYPE_2_6B; break;
                     default:   type = LLM_TYPE_UNKNOWN;
                 }
             } break;

diff --git a/src/llama-model.h b/src/llama-model.h
index b1981978e3acf8753a96dceff561b1f6e5060cdf..db9a83b34ea79aada0b1db1ace2d0e40f59aeb78 100644 (file)
--- a/src/llama-model.h
+++ b/src/llama-model.h
@@ -58,6 +58,7 @@ enum llm_type {
     LLM_TYPE_1_7B,
     LLM_TYPE_1_8B,
     LLM_TYPE_2B,
+    LLM_TYPE_2_6B,
     LLM_TYPE_2_8B,
     LLM_TYPE_2_9B,
     LLM_TYPE_3B,