Update README.md

README.md

@@ -97,7 +97,7 @@ pip3 install huggingface-hub
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 
 ```shell
-huggingface-cli download MaziyarPanahi/jaskier-7b-dpo-v5.6-GGUF jaskier-7b-dpo-v5.6-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+huggingface-cli download MaziyarPanahi/jaskier-7b-dpo-v5.6-GGUF jaskier-7b-dpo-v5.6.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 </details>
 <details>
@@ -120,7 +120,7 @@ pip3 install hf_transfer
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 
 ```shell
-HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/jaskier-7b-dpo-v5.6-GGUF jaskier-7b-dpo-v5.6-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/jaskier-7b-dpo-v5.6-GGUF jaskier-7b-dpo-v5.6.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
 Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
@@ -131,7 +131,7 @@ Windows Command Line users: You can set the environment variable by running `set
 Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 35 -m jaskier-7b-dpo-v5.6-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
+./main -ngl 35 -m jaskier-7b-dpo-v5.6.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
 {system_message}<|im_end|>
 <|im_start|>user
 {prompt}<|im_end|>
@@ -188,7 +188,7 @@ from llama_cpp import Llama
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
 llm = Llama(
-  model_path="./jaskier-7b-dpo-v5.6-GGUF.Q4_K_M.gguf",  # Download the model file first
+  model_path="./jaskier-7b-dpo-v5.6.Q4_K_M.gguf",  # Download the model file first
   n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources
   n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance
   n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available
@@ -208,7 +208,7 @@ output = llm(
 
 # Chat Completion API
 
-llm = Llama(model_path="./jaskier-7b-dpo-v5.6-GGUF.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm = Llama(model_path="./jaskier-7b-dpo-v5.6.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
 llm.create_chat_completion(
     messages = [
         {"role": "system", "content": "You are a story writing assistant."},