model: codefuse-ai/F2LLM-v2 support

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 06365bb498bbba35f11b210d2bf9dc21755f4b94..cb255763da2b7bba6983dd0b31b1ce42fede4abd 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -1503,6 +1503,9 @@ class TextModel(ModelBase):
         if chkhsh == "e4d54df1ebc1f2b91acd986c5b51aa50837d5faf7c7398e73c1f9e9ee5d19869":
             # ref: https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct-2601
             res = "kanana2"
+        if chkhsh == "862f827721df956049dff5ca81a57f29e575280bc622e290d3bf4e35eca29015":
+            # ref: https://huggingface.co/codefuse-ai/F2LLM-v2-4B
+            res = "f2llmv2"
 
         if res is None:
             logger.warning("\n")

diff --git a/convert_hf_to_gguf_update.py b/convert_hf_to_gguf_update.py
index b31ddcca774f9d5992639a14b68a8bca28f94756..1e8b29fb2ec0cece34b934e70cbb44f470d1f27b 100755 (executable)
--- a/convert_hf_to_gguf_update.py
+++ b/convert_hf_to_gguf_update.py
@@ -154,6 +154,7 @@ models = [
     {"name": "qwen35",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen3.5-9B-Instruct", },
     {"name": "joyai-llm",        "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jdopensource/JoyAI-LLM-Flash", },
     {"name": "kanana2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/kakaocorp/kanana-2-30b-a3b-instruct-2601", },
+    {"name": "f2llmv2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/codefuse-ai/F2LLM-v2-4B", },
 ]
 
 # some models are known to be broken upstream, so we will skip them as exceptions

diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp
index 13934339dd43fecacc525c85e065ee96d3af3fdf..e5e414172a082c933db4d686b035b0529b20d33e 100644 (file)
--- a/src/llama-vocab.cpp
+++ b/src/llama-vocab.cpp
@@ -1952,7 +1952,8 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) {
             } else if (
                     tokenizer_pre == "qwen2" ||
                     tokenizer_pre == "deepseek-r1-qwen" ||
-                    tokenizer_pre == "kormo") {
+                    tokenizer_pre == "kormo" ||
+                    tokenizer_pre == "f2llmv2") {
                 pre_type = LLAMA_VOCAB_PRE_TYPE_QWEN2;
                 clean_spaces = false;
             } else if (