Update README.md

app.py

@@ -11,8 +11,9 @@ from pathlib import Path
 from textwrap import dedent
 from apscheduler.schedulers.background import BackgroundScheduler
 
-# used for restarting the space
-SPACE_ID = os.environ.get("SPACE_ID")
+# Space parameters
+SPACE_ID = os.environ.get("SPACE_ID") if os.environ.get("SPACE_ID") else ""
+SPACE_URL = "https://" + SPACE_ID.replace("/", "-") + ".hf.space/" if SPACE_ID else "http://localhost:7860/"
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
 # Folder
@@ -44,6 +45,9 @@ def escape(s: str) -> str:
     s = s.replace("\n", "<br/>")
     return s
 
+def get_model_creator(model_id: str):
+    return model_id.split('/')[0]
+
 def get_model_name(model_id: str):
     return model_id.split('/')[-1]
 
@@ -251,6 +255,9 @@ def quantize_model(
     return quantized_gguf
 
 def generate_readme(outdir: tempfile.TemporaryDirectory, token: str, model_id: str, new_repo_id: str, gguf_name: str):
+    creator = get_model_creator(model_id)
+    model_name = get_model_name(model_id)
+
     try:
         card = ModelCard.load(model_id, token=token)
     except:
@@ -264,57 +271,39 @@ def generate_readme(outdir: tempfile.TemporaryDirectory, token: str, model_id: s
     card.data.base_model = model_id
     card.text = dedent(
         f"""
-        # {new_repo_id}
-        This model was converted to GGUF format from [`{model_id}`](https://huggingface.co/{model_id}) 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/{model_id}) for more details on the model.
-
-        ## Use with ollama
-        Install ollama from the [official website](https://ollama.com/).
-
-        Run the model on the CLI.
-        ```sh
-        ollama run hf.co/{model_id}
-        ```
-
-        ## Use with llama.cpp
-        Install llama.cpp through brew (works on Mac and Linux)
-
-        ```bash
-        brew install llama.cpp
-
-        ```
-        Invoke the llama.cpp server or the CLI.
-
-        ### CLI:
-        ```bash
-        llama-cli --hf-repo {new_repo_id} --hf-file {gguf_name} -p "The meaning to life and the universe is"
-        ```
-
-        ### Server:
-        ```bash
-        llama-server --hf-repo {new_repo_id} --hf-file {gguf_name} -c 2048
-        ```
-
-        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.
-
-        Step 1: Clone llama.cpp from GitHub.
-        ```
-        git clone https://github.com/ggerganov/llama.cpp
-        ```
-
-        Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-        ```
-        cd llama.cpp && LLAMA_CURL=1 make
-        ```
-
-        Step 3: Run inference through the main binary.
-        ```
-        ./llama-cli --hf-repo {new_repo_id} --hf-file {gguf_name} -p "The meaning to life and the universe is"
-        ```
-        or
-        ```
-        ./llama-server --hf-repo {new_repo_id} --hf-file {gguf_name} -c 2048
-        ```
+# {model_name}
+
+**Model creator:** [{creator}](https://huggingface.co/{creator})
+**Original model**: [{model_id}](https://huggingface.co/{model_id})
+**GGUF quantization:** provided by [{SPACE_ID}](https:/huggingface.co/spaces/{SPACE_ID}) team using `llama.cpp`
+
+## Special thanks
+
+🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
+
+## Use with Ollama
+
+```bash
+ollama run hf.co/{new_repo_id}:<quantization>
+```
+
+## Use with LM Studio
+
+```bash
+lms load {new_repo_id}
+```
+
+## Use with llama.cpp CLI
+
+```bash
+llama-cli --hf-repo {new_repo_id} --hf-file {gguf_name} -p "The meaning to life and the universe is"
+```
+
+## Use with llama.cpp Server:
+
+```bash
+llama-server --hf-repo {new_repo_id} --hf-file {gguf_name} -c 4096
+```
         """
     )
     readme_path = Path(outdir)/"README.md"
@@ -602,7 +591,7 @@ with gr.Blocks(css=css) as demo:
     gr.LoginButton(min_width=250)
 
     gr.HTML("<h1 style=\"text-aling:center;\">Create your own GGUF Quants!</h1>")
-    gr.Markdown("The space takes an HF repo as an input, quantizes it and creates a Public repo containing the selected quant under your HF user namespace.")
+    gr.Markdown(f"The space takes an HF repo as an input, quantizes it and creates a Public repo containing the selected quant under your HF user namespace. Use via {SPACE_URL}")
 
     with gr.Row():
         with gr.Column() as inputs: