Added gemma 2 GGUF model.

Author: souradipp76

doc_generator/types.py

@@ -24,6 +24,7 @@ class LLMModels(str, Enum):
     GOOGLE_GEMMA_7B_INSTRUCT = "google/gemma-7b-it"
     GOOGLE_CODEGEMMA_2B_INSTRUCT = "google/codegemma-2b-it"
     GOOGLE_CODEGEMMA_7B_INSTRUCT = "google/codegemma-7b-it"
+    GOOGLE_GEMMA_2B_INSTRUCT_GGUF = "bartowski/gemma-2-2b-it-GGUF"
 
 
 class Priority(str, Enum):

doc_generator/utils/llm_utils.py

@@ -310,6 +310,19 @@ def get_tokenizer(model_name: str, gguf_file=None):
         failed=0,
         total=0,
     ),
+    LLMModels.GOOGLE_GEMMA_2B_INSTRUCT_GGUF: LLMModelDetails(
+        name=LLMModels.GOOGLE_GEMMA_2B_INSTRUCT_GGUF,
+        input_cost_per_1k_tokens=0,
+        output_cost_per_1k_tokens=0,
+        max_length=8192,
+        llm=None,
+        input_tokens=0,
+        output_tokens=0,
+        succeeded=0,
+        failed=0,
+        total=0,
+        gguf_file="gemma-2-2b-it-IQ3_M.gguf"
+    ),
 }