model: add Solar Open model (#18511)

* model: add Solar-Open model

* vocab: add solar-open to end eog blacklist

* model: add proper llm type

* chat: basic template for solar open

* typo: fix comment about vocab

* convert: sugested changes

* convert: suggested changes

* chat: change reasoning end tag for solar-open

* llama-chat: add solar-open template

convert_hf_to_gguf.py

@@ -1230,6 +1230,9 @@ class TextModel(ModelBase):
         if chkhsh == "4a2e2abae11ca2b86d570fc5b44be4d5eb5e72cc8f22dd136a94b37da83ab665":
             # ref: https://huggingface.co/KORMo-Team/KORMo-tokenizer
             res = "kormo"
+        if chkhsh == "16389f0a1f51ee53e562ffd51c371dc508639ab0e4261502071836e50e223e91":
+            # ref: https://huggingface.co/upstage/Solar-Open-100B
+            res = "solar-open"
 
         if res is None:
             logger.warning("\n")
@@ -10617,6 +10620,26 @@ class JanusProVisionModel(MmprojModel):
         return []
 
 
+@ModelBase.register("SolarOpenForCausalLM")
+class SolarOpenModel(Glm4MoeModel):
+    model_arch = gguf.MODEL_ARCH.GLM4_MOE
+
+    def set_vocab(self):
+        from transformers import AutoTokenizer
+        tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
+        special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True)
+        tokens, toktypes, tokpre = self.get_vocab_base()
+        self.gguf_writer.add_tokenizer_model("gpt2")
+        self.gguf_writer.add_tokenizer_pre(tokpre)
+        self.gguf_writer.add_token_list(tokens)
+        self.gguf_writer.add_token_types(toktypes)
+        special_vocab._set_special_token("eos", tokenizer.get_added_vocab()["<|endoftext|>"])
+        special_vocab._set_special_token("eot", tokenizer.get_added_vocab()["<|endoftext|>"])
+        special_vocab._set_special_token("unk", tokenizer.get_added_vocab()["<unk>"])
+        special_vocab._set_special_token("bos", tokenizer.get_added_vocab()["<|startoftext|>"])
+        special_vocab.add_to_gguf(self.gguf_writer)
+
+
 ###### CONVERSION LOGIC ######