Update README.md

README.md

@@ -1,7 +1,6 @@
 ---
-library_name: transformers
 license: mit
-base_model: XeTute/Phantasor_V0.1-137M
+base_model: openai-community/gpt2
 tags:
 - llama-factory
 - full
@@ -10,8 +9,6 @@ tags:
 - tiny
 - chinese
 - english
-- llama-cpp
-- gguf-my-repo
 datasets:
 - Chamoda/atlas-storyteller-1000
 - jaydenccc/AI_Storyteller_Dataset
@@ -22,46 +19,37 @@ language:
 pipeline_tag: text-generation
 ---
 
-# XeTute/Phantasor_V0.1-137M-Q8_0-GGUF
-This model was converted to GGUF format from [`XeTute/Phantasor_V0.1-137M`](https://huggingface.co/XeTute/Phantasor_V0.1-137M) 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/XeTute/Phantasor_V0.1-137M) for more details on the model.
+> [!TIP]
+> Model is still in its testing phase. We don't recommend it for high-end production enviroments, it's only a model for story-generation.  
+> Model trained using LLaMA-Factory by Asadullah Hamzah at XeTute Technologies.
 
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+# Phantasor V0.1
+We introduce Phantasor V0.1, our first sub-1B Parameter GPT. It has been trained ontop of GPT2's smallest version using a little bit over 1.5B input tokens.  
+Licensed under MIT, feel free to use it in your personal projects, both commercially and privately, Since this is V0.1, we're open to feedback to improve our project(s). **The Chat-Template used is Alpaca (### Instruction [...]).**  
+[You can find the FP32 version here.](https://huggingface.co/XeTute/Phantasor_V0.1-137M)  
 
-```bash
-brew install llama.cpp
+## Training
+This model was trained on all samples, tokens included in:  
+- [Chamoda/atlas-storyteller-1000](https://huggingface.co/datasets/Chamoda/atlas-storyteller-1000)  
+- [jaydenccc/AI_Storyteller_Dataset](https://huggingface.co/datasets/jaydenccc/AI_Storyteller_Dataset)  
+- [zxbsmk/webnovel_cn](https://huggingface.co/datasets/zxbsmk/webnovel_cn)
 
-```
-Invoke the llama.cpp server or the CLI.
+for exactly 3.0 epochs on all model parameters. Following is the loss curve, updated with each training step over all three epochs.
+![training_loss.png](https://huggingface.co/XeTute/Phantasor_V0.1-137M/resolve/main/training_loss.png)
+Instead of AdamW, which is often used for large GPTs, we used **SGD**, which enabled the model to generalize better, which can be seen when using the model on non-dataset prompts.  
 
-### CLI:
-```bash
-llama-cli --hf-repo XeTute/Phantasor_V0.1-137M-Q8_0-GGUF --hf-file phantasor_v0.1-137m-q8_0.gguf -p "The meaning to life and the universe is"
-```
+## Finished Model
+- ~137M Parameters, all of which are trainable  
+- 1024 / 1k input tokens / context length, from which all were used  
+- A loss 2.2 on all samples
 
-### Server:
-```bash
-llama-server --hf-repo XeTute/Phantasor_V0.1-137M-Q8_0-GGUF --hf-file phantasor_v0.1-137m-q8_0.gguf -c 2048
-```
+This is solid performance for a model with only 137M parameters.
 
-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.
+# Our platforms
+## Socials  
+[BlueSky](https://bsky.app/profile/xetute.bsky.social) | [YouTube](https://www.youtube.com/@XeTuteTechnologies) | [HuggingFace 🤗](https://huggingface.co/XeTute) | [Ko-Fi / Financially Support Us](https://ko-fi.com/XeTute)
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+## Our Platforms  
+[Our Webpage](https://xetute.com) | [PhantasiaAI](https://xetute.com/PhantasiaAI)
 
-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 XeTute/Phantasor_V0.1-137M-Q8_0-GGUF --hf-file phantasor_v0.1-137m-q8_0.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo XeTute/Phantasor_V0.1-137M-Q8_0-GGUF --hf-file phantasor_v0.1-137m-q8_0.gguf -c 2048
-```
+Have a great day!