Update README.md

README.md

@@ -2500,9 +2500,14 @@ model-index:
 ---
 
 # Plasmoxy/bge-micro-v2-Q4_K_M-GGUF
+
+Really small BGE embedding model but with 4-bit gguf quant.
+
 This model was converted to GGUF format from [`TaylorAI/bge-micro-v2`](https://huggingface.co/TaylorAI/bge-micro-v2) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/TaylorAI/bge-micro-v2) for more details on the model.
 
+**!!! IMPORTANT !!! - context size is 512, specify the context size (-c 512) for llama cpp.**
+
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)
 
@@ -2514,12 +2519,12 @@ Invoke the llama.cpp server or the CLI.
 
 ### CLI:
 ```bash
-llama-cli --hf-repo Plasmoxy/bge-micro-v2-Q4_K_M-GGUF --hf-file bge-micro-v2-q4_k_m.gguf -p "The meaning to life and the universe is"
+llama-cli --hf-repo Plasmoxy/bge-micro-v2-Q4_K_M-GGUF --hf-file bge-micro-v2-q4_k_m.gguf -c 512 -p "The meaning to life and the universe is"
 ```
 
 ### Server:
 ```bash
-llama-server --hf-repo Plasmoxy/bge-micro-v2-Q4_K_M-GGUF --hf-file bge-micro-v2-q4_k_m.gguf -c 2048
+llama-server --hf-repo Plasmoxy/bge-micro-v2-Q4_K_M-GGUF --hf-file bge-micro-v2-q4_k_m.gguf -c 512
 ```
 
 Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.