Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: chimbiwide/Gemma3NPC-it-beta
+base_model: chimbiwide/gemma-3NPC-it-beta
 tags:
 - text-generation-inference
 - transformers
@@ -14,46 +14,32 @@ datasets:
 - chimbiwide/RolePlay-NPC
 ---
 
-# chimbiwide/Gemma3NPC-it-beta-Q8_0-GGUF
-This model was converted to GGUF format from [`chimbiwide/Gemma3NPC-it-beta`](https://huggingface.co/chimbiwide/Gemma3NPC-it-beta) 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/chimbiwide/Gemma3NPC-it-beta) for more details on the model.
-
-## 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 chimbiwide/Gemma3NPC-it-beta-Q8_0-GGUF --hf-file gemma3npc-it-beta-q8_0.gguf -p "The meaning to life and the universe is"
-```
-
-### Server:
-```bash
-llama-server --hf-repo chimbiwide/Gemma3NPC-it-beta-Q8_0-GGUF --hf-file gemma3npc-it-beta-q8_0.gguf -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 chimbiwide/Gemma3NPC-it-beta-Q8_0-GGUF --hf-file gemma3npc-it-beta-q8_0.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo chimbiwide/Gemma3NPC-it-beta-Q8_0-GGUF --hf-file gemma3npc-it-beta-q8_0.gguf -c 2048
-```
+# Gemma3NPC-it-beta
+
+#### A test model with less convervative training parameters
+
+The Q8_0 quantized version of `Gemma3NPC-it-beta-Float16`. 
+
+As mentioned in our [original article](https://huggingface.co/blog/chimbiwide/gemma3npc), we employed a very conservative training parameters for Gemma3NPC
+
+Ever since then, we have always wanted to test the performance of the model when we make the training parameters less conservative. 
+
+So we present ***Gemma3NPC-it-beta***.
+
+Check out our training notebook [here](https://github.com/chimbiwide/Gemma3NPC/blob/main/Training/Gemma3NPC_Instruct_Beta.ipynb)
+
+---
+
+#### Training parameters compared to `Gemma3NPC-it`
+
+| Parameter | Gemma3NPC-it | Gemma3NPC-it-beta |
+| --- | --- | --- | 
+| Learning Rate | 2e-5 | 2.5e-5 (+25%) | 
+| Warmup Steps | 800 | 100 |
+| gradient clipping | 0.4 | 1.0 |
+
+---
+
+Here is a graph of the Step Training Loss, saved every 10 steps:
+
+![chart](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/W3cJ_CPoLp9MZsomaZa3b.png)