Update README.md

README.md

@@ -114,7 +114,17 @@ model-index:
 ---
 # orca_mini_3b
 
-Use orca-mini-3b on Free Google Colab with T4 GPU :)
+<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
+
+<strong>
+Passionate about Generative AI? I help companies to privately train and deploy custom LLM/MLLM affordably. For startups, I can even assist with securing GPU grants to get you started. Let's chat!
+
+<a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a> Looking forward to connecting!
+</strong>
+
+<br>
+
+**Use orca-mini-3b for Free on Google Colab with T4 GPU :)**
 
 <a target="_blank" href="https://colab.research.google.com/#fileId=https://huggingface.co/psmathur/orca_mini_3b/blob/main/orca_mini_3b_T4_GPU.ipynb">
   <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
@@ -123,7 +133,7 @@ Use orca-mini-3b on Free Google Colab with T4 GPU :)
 An [OpenLLaMa-3B model](https://github.com/openlm-research/open_llama) model trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.
 
 
-# Dataset
+### Dataset
 
 We build explain tuned [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html)  & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
 
@@ -134,7 +144,7 @@ This helps student model aka this model to learn ***thought*** process from teac
 Please see below example usage how the **System** prompt is added before each **instruction**.
 
 
-# Training
+### Training
 
 The training configurations are provided in the table below.
 
@@ -156,7 +166,7 @@ Here are some of params used during training:
 
 
 
-# Example Usage
+### Example Usage
 
 Below shows an example on how to use this model
 
@@ -230,8 +240,6 @@ Sincerely,
 ```
 
 
-**P.S. I am #opentowork and #collaboration, if you can help, please reach out to me at www.linkedin.com/in/pankajam**
-
 
 Next Goals:
 1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
@@ -304,7 +312,7 @@ If you found wizardlm_alpaca_dolly_orca_open_llama_3b useful in your research or
   howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
 }
 ```
-# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_3b)
 
 | Metric                | Value                     |
@@ -318,7 +326,7 @@ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-le
 | GSM8K (5-shot)        | 0.08        |
 | DROP (3-shot)         | 14.33         |
 
-# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_3b)
 
 |             Metric              |Value|