Upload README.md

README.md

@@ -5,7 +5,7 @@ datasets:
 inference: false
 language:
 - en
-license: apache-2.0
+license: other
 model_creator: Eric Hartford
 model_name: Based 30B
 model_type: llama
@@ -86,15 +86,8 @@ ASSISTANT:
 ```
 
 <!-- prompt-template end -->
-<!-- licensing start -->
-## Licensing
 
-The creator of the source model has listed its license as `apache-2.0`, and this quantization has therefore used that same license.
 
-As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
-
-In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Eric Hartford's Based 30B](https://huggingface.co/ehartford/based-30b).
-<!-- licensing end -->
 <!-- compatibility_gguf start -->
 ## Compatibility
 
@@ -153,7 +146,7 @@ The following clients/libraries will automatically download models for you, prov
 
 ### In `text-generation-webui`
 
-Under Download Model, you can enter the model repo: TheBloke/based-30B-GGUF and below it, a specific filename to download, such as: based-30b.q4_K_M.gguf.
+Under Download Model, you can enter the model repo: TheBloke/based-30B-GGUF and below it, a specific filename to download, such as: based-30b.Q4_K_M.gguf.
 
 Then click Download.
 
@@ -168,7 +161,7 @@ pip3 install huggingface-hub>=0.17.1
 Then you can download any individual model file to the current directory, at high speed, with a command like this:
 
 ```shell
-huggingface-cli download TheBloke/based-30B-GGUF based-30b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+huggingface-cli download TheBloke/based-30B-GGUF based-30b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
 <details>
@@ -191,7 +184,7 @@ pip3 install hf_transfer
 And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
 
 ```shell
-HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/based-30B-GGUF based-30b.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/based-30B-GGUF based-30b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
 ```
 
 Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.
@@ -204,7 +197,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
 Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 32 -m based-30b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an an AI who shares your opinions, thoughts, and feelings.\n\nUSER: {prompt}\nASSISTANT:"
+./main -ngl 32 -m based-30b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an an AI who shares your opinions, thoughts, and feelings.\n\nUSER: {prompt}\nASSISTANT:"
 ```
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -244,7 +237,7 @@ CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
 from ctransformers import AutoModelForCausalLM
 
 # 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 = AutoModelForCausalLM.from_pretrained("TheBloke/based-30B-GGUF", model_file="based-30b.q4_K_M.gguf", model_type="llama", gpu_layers=50)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/based-30B-GGUF", model_file="based-30b.Q4_K_M.gguf", model_type="llama", gpu_layers=50)
 
 print(llm("AI is going to"))
 ```