38d3509ce766513f2f506d576c12c8ee6150c9208cc80644b969f9b9a2f7d5d5

README.md

@@ -10,6 +10,7 @@ tags:
 - GGUF
 - transformers
 - pytorch
+- safetensors
 - llama
 - text-generation
 - en
@@ -98,7 +99,7 @@ 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/tulu-2-dpo-13b-GGUF tulu-2-dpo-13b-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+huggingface-cli download MaziyarPanahi/tulu-2-dpo-13b-GGUF tulu-2-dpo-13b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 </details>
 <details>
@@ -121,7 +122,7 @@ 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/tulu-2-dpo-13b-GGUF tulu-2-dpo-13b-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/tulu-2-dpo-13b-GGUF tulu-2-dpo-13b.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.
@@ -132,7 +133,7 @@ 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 tulu-2-dpo-13b-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 tulu-2-dpo-13b.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|>
@@ -149,7 +150,7 @@ For other parameters and how to use them, please refer to [the llama.cpp documen
 
 ## How to run in `text-generation-webui`
 
-Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
+Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20-%20Model%20Tab.md#llamacpp).
 
 ## How to run from Python code
 
@@ -157,7 +158,7 @@ You can use GGUF models from Python using the [llama-cpp-python](https://github.
 
 ### How to load this model in Python code, using llama-cpp-python
 
-For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
+For full documentation, please see: [llama-cpp-python docs](https://github.com/abetlen/llama-cpp-python/).
 
 #### First install the package
 
@@ -189,7 +190,7 @@ 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="./tulu-2-dpo-13b-GGUF.Q4_K_M.gguf",  # Download the model file first
+  model_path="./tulu-2-dpo-13b.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
@@ -209,7 +210,7 @@ output = llm(
 
 # Chat Completion API
 
-llm = Llama(model_path="./tulu-2-dpo-13b-GGUF.Q4_K_M.gguf", chat_format="llama-2")  # Set chat_format according to the model you are using
+llm = Llama(model_path="./tulu-2-dpo-13b.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."},