llama: add support for small granite models

it works only for the small models 3b and 8b.

The convert-hf-to-gguf.py script uses the vocabulary size of the
granite models to detect granite and set the correct configuration.

Signed-off-by: Giuseppe Scrivano <[email protected]>

Author: giuseppe

convert-hf-to-gguf.py

@@ -1322,6 +1322,10 @@ def set_gguf_parameters(self):
                 if "add_prefix_space" in tokenizer_config_json:
                     self.gguf_writer.add_add_space_prefix(tokenizer_config_json["add_prefix_space"])
 
+        # Apply to granite small models only
+        if self.hparams.get("vocab_size", 32000) == 49152:
+            self.gguf_writer.add_add_bos_token(False)
+
     @staticmethod
     def permute(weights: Tensor, n_head: int, n_head_kv: int | None):
         if n_head_kv is not None and n_head != n_head_kv:
@@ -1336,9 +1340,9 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         n_head = self.hparams["num_attention_heads"]
         n_kv_head = self.hparams.get("num_key_value_heads")
 
-        if name.endswith("q_proj.weight"):
+        if name.endswith(("q_proj.weight", "q_proj.bias")):
             data_torch = LlamaModel.permute(data_torch, n_head, n_head)
-        if name.endswith("k_proj.weight"):
+        if name.endswith(("k_proj.weight", "k_proj.bias")):
             data_torch = LlamaModel.permute(data_torch, n_head, n_kv_head)
 
         # process the experts separately

llama.cpp

@@ -3982,7 +3982,9 @@ static void llm_load_hparams(
                     switch (hparams.n_layer) {
                         case 22: model.type = e_model::MODEL_1B; break;
                         case 26: model.type = e_model::MODEL_3B; break;
-                        case 32: model.type = hparams.n_vocab < 40000 ? e_model::MODEL_7B : e_model::MODEL_8B; break;
+                        // granite uses a vocab with len 49152
+                        case 32: model.type = hparams.n_vocab == 49152 ? e_model::MODEL_3B : (hparams.n_vocab < 40000 ? e_model::MODEL_7B : e_model::MODEL_8B); break;
+                        case 36: model.type = e_model::MODEL_8B; break; // granite
                         case 40: model.type = e_model::MODEL_13B; break;
                         case 48: model.type = e_model::MODEL_34B; break;
                         case 60: model.type = e_model::MODEL_30B; break;
@@ -4252,6 +4254,8 @@ static void llm_load_hparams(
                     case 30: model.type = e_model::MODEL_3B; break;
                     case 32: model.type = e_model::MODEL_7B; break;
                     case 40: model.type = e_model::MODEL_15B; break;
+                    case 52: model.type = e_model::MODEL_20B; break; // granite
+                    case 88: model.type = e_model::MODEL_34B; break; // granite
                     default: model.type = e_model::MODEL_UNKNOWN;
                 }
             } break;