Update README.md

README.md

@@ -14,7 +14,7 @@ language:
 pipeline_tag: text-generation
 ---
 
-# DiTy/gemma-2-2b-it-function-calling
+# DiTy/gemma-2-2b-it-function-calling-GGUF
 
 > NB: If you want to use the model to call functions in complex, long and confusing dialogues, it is better to use a larger model [DiTy/gemma-2-9b-it-function-calling-GGUF](https://huggingface.co/DiTy/gemma-2-9b-it-function-calling-GGUF).  
 
@@ -22,6 +22,14 @@ This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface
 fully annotated by humans only, on the English version of the <ins>*DiTy/function-calling*</ins> dataset.
 <!-- Provide a quick summary of what the model is/does. -->
 
+In addition to **safetensors**, the model is available in **GGUF** formats (in this case, you need to download only a single file), 
+*however, it should be borne in mind that this model itself was difficult to master "Function Calling", so it is not recommended to use heavily quantized versions*:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [gemma-2-2B-it-function-calling-F16.gguf](https://huggingface.co/DiTy/gemma-2-2b-it-function-calling-GGUF/blob/main/gemma-2-2B-it-function-calling-F16.gguf) | F16 | 18.5GB | Base model with float16 *recommended* |
+| [gemma-2-2B-it-function-calling-Q8_0.gguf](https://huggingface.co/DiTy/gemma-2-2b-it-function-calling-GGUF/blob/main/gemma-2-2B-it-function-calling-Q8_0.gguf) | Q8_0 | 9.83GB | Extremely high quality, generally unneeded but max available quant. |
+
 ## Model card tree
 
 * [How prepare your functions (tools) for *Function Calling*](#prepare_func_call)
@@ -71,13 +79,13 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 model = AutoModelForCausalLM.from_pretrained(
-    "DiTy/gemma-2-2b-it-function-calling",
+    "DiTy/gemma-2-2b-it-function-calling-GGUF",
     device_map="auto",
     torch_dtype=torch.bfloat16,  # use float16 or float32 if bfloat16 is not available to you.
     cache_dir=PATH_TO_MODEL_DIR,  # optional
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "DiTy/gemma-2-2b-it-function-calling",
+    "DiTy/gemma-2-2b-it-function-calling-GGUF",
     cache_dir=PATH_TO_MODEL_DIR,  # optional
 )
 ```
@@ -262,7 +270,7 @@ from transformers import pipeline
 
 generation_pipeline = pipeline(
     "text-generation",
-    model="DiTy/gemma-2-2b-it-function-calling",
+    model="DiTy/gemma-2-2b-it-function-calling-GGUF",
     model_kwargs={
         "torch_dtype": torch.bfloat16,  # use float16 or float32 if bfloat16 is not supported for you. 
         "cache_dir": PATH_TO_MODEL_DIR,  # OPTIONAL
@@ -401,7 +409,7 @@ During the learning process, the validation error was approximated to the follow
 | **Model** | **Generation Language** | **Approximately Validation Loss** |
 | :-----: | :-----: | :-----: |
 | [DiTy/gemma-2-9b-it-function-calling-GGUF](https://huggingface.co/DiTy/gemma-2-9b-it-function-calling-GGUF) | EN | 0.5 |
-| **[DiTy/gemma-2-2b-it-function-calling](https://huggingface.co/DiTy/gemma-2-2b-it-function-calling)** | EN | 0.66 |
+| **[DiTy/gemma-2-2b-it-function-calling-GGUF](https://huggingface.co/DiTy/gemma-2-2b-it-function-calling-GGUF)** | EN | 0.66 |
 
 ## Citation