Update README.md

README.md

@@ -47,41 +47,6 @@ This repo contains `GGUF` format model files for [aisingapore/llama3.1-8b-cpt-se
 - [llama3.1-8b-cpt-sea-lionv3-instruct-Q6_K](https://huggingface.co/aisingapore/llama3.1-8b-cpt-sea-lionv3-instruct-gguf/blob/main/llama3.1-8B-cpt-sea-lionv3-instruct-Q6_K.gguf)
 - [llama3.1-8b-cpt-sea-lionv3-instruct-Q8_0](https://huggingface.co/aisingapore/llama3.1-8b-cpt-sea-lionv3-instruct-gguf/blob/main/llama3.1-8B-cpt-sea-lionv3-instruct-Q8_0.gguf)
 
-### Usage
-Llama 3.1 8B CPT SEA-Lionv3 Instruct GGUF files have been tested with [llama.cpp](https://github.com/ggerganov/llama.cpp).
-
-#### Prompt Template:
-```
-<|begin_of_text|><|start_header_id|>system<|end_header_id|>
-
-{{system_prompt}}<|eot_id|>
-<|start_header_id|>user<|end_header_id|>
-
-{{prompt}}<|eot_id|>
-<|start_header_id|>assistant<|end_header_id|>
-```
-
-#### Recommended `llama.cpp` command:
-To execute the following commands, ensure you are in the `llama.cpp` root directory and that your models are located in the `models` folder:
-```sh
-# Running one-time input prompt
-./llama-cli -m models/llama3.1-8b-cpt-sea-lionv3-instruct-gguf/llama3.1-8b-cpt-sea-lionv3-instruct-Q4_K_M.gguf -ngl -1 --temp 0 -n 128 -p "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant who answers succinctly.<|eot_id|>\n<|start_header_id|>user<|end_header_id|>\n\nWhat is a sea lion?<|eot_id|>\n<|start_header_id|>assistant<|end_header_id|>\n\n"
-```
-```sh
-# Running in conversation mode
-./llama-cli -m models/llama3.1-8b-cpt-sea-lionv3-instruct-gguf/llama3.1-8b-cpt-sea-lionv3-instruct-Q4_K_M.gguf -ngl -1 --temp 0 -n 128 -p "You are a helpful assistant who answers succinctly." --color -cnv --chat-template llama3
-```
-Please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) for adjusting the parameters.
-
-#### To convert & quantize your own SEA-LION model:
-Given that you are in the `llama.cpp` root directory:
-```sh
-python convert-hf-to-gguf.py {{model path}}
-./quantize ggml-model-f16.gguf {{Quant Type}}
-```
-
-For more detailed instructions on conversion and quantization, please refer to [llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/quantize/README.md).
-
 ### Caveats
 It is important for users to be aware that our model exhibits certain limitations that warrant consideration. Like many LLMs, the model can hallucinate and occasionally generates irrelevant content, introducing fictional elements that are not grounded in the provided context. Users should also exercise caution in interpreting and validating the model's responses due to the potential inconsistencies in its reasoning.