Update README.md

README.md

@@ -3,6 +3,12 @@ language:
 - en
 library_name: transformers
 license: llama2
+datasets:
+- pankajmathur/orca_mini_v1_dataset
+- pankajmathur/dolly-v2_orca
+- pankajmathur/WizardLM_Orca
+- pankajmathur/alpaca_orca
+- ehartford/dolphin
 ---
 
 
@@ -30,7 +36,7 @@ A hybrid (explain + instruct) style Llama2-70b model, Pleae check examples below
 
 
 ### quantized versions
-Huge respect to man.. @TheBloke, here are the GGML/GPTQ/GGUF versions, go crazy :)
+Huge respect to @TheBloke, here are the GGML/GPTQ/GGUF versions, go crazy :)
 
 https://huggingface.co/TheBloke/model_007-70B-GGML
 
@@ -52,19 +58,22 @@ We evaluated model_007 on a wide range of tasks using [Language Model Evaluation
 
 Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 
-|||||
-|:------:|:--------:|:-------:|:--------:|
-|**Task**|**Metric**|**Value**|**Stderr**|
-|*arc_challenge*|acc_norm|0.7108|0.0141|
-|*hellaswag*|acc_norm|0.8765|0.0038|
-|*mmlu*|acc_norm|0.6904|0.0351|
-|*truthfulqa_mc*|mc2|0.6312|0.0157|
-|**Total Average**|-|**0.72729**||
+|||
+|:------:|:--------:|
+|**Task**|**Value**|
+|*ARC*|0.7108|
+|*HellaSwag*|0.8765|
+|*MMLU*|0.6904|
+|*TruthfulQA*|0.6312|
+|*Winogrande*|0.8335|
+|*GSM8K*|0.3715|
+|*DROP*|0.3105|
+|**Total Average**|**0.6320**|
 
 
 <br>
 
-## Example Usage
+## Prompt Format
 
 Here is the Orca prompt format
 
@@ -79,7 +88,35 @@ Tell me about Orcas.
 
 ```
 
-Below shows a code example on how to use this model
+Here is the Alpaca prompt format
+
+```
+
+### User:
+Tell me about Alpacas.
+
+### Assistant:
+
+```
+
+#### OobaBooga Instructions:
+
+This model required upto 45GB GPU VRAM in 4bit so it can be loaded directly on Single RTX 6000/L40/A40/A100/H100 GPU or Double RTX 4090/L4/A10/RTX 3090/RTX A5000
+So, if you have access to Machine with 45GB GPU VRAM and have installed [OobaBooga Web UI](https://github.com/oobabooga/text-generation-webui) on it.
+You can just download this model by using HF repo link directly on OobaBooga Web UI "Model" Tab/Page & Just use **load-in-4bit** option in it.
+
+![model_load_screenshot](https://huggingface.co/pankajmathur/model_101/resolve/main/oobabooga_model_load_screenshot.png)
+
+
+After that go to Default Tab/Page on OobaBooga Web UI and **copy paste above prompt format into Input** and Enjoy!
+
+![default_input_screenshot](https://huggingface.co/pankajmathur/model_101/resolve/main/default_input_screenshot.png)
+
+<br>
+
+#### Code Instructions:
+
+Below shows a code example on how to use this model via Orca prompt
 
 ```python
 import torch
@@ -105,19 +142,7 @@ print(tokenizer.decode(output[0], skip_special_tokens=True))
 
 ```
 
-
-Here is the Alpaca prompt format
-
-```
-
-### User:
-Tell me about Alpacas.
-
-### Assistant:
-
-```
-
-Below shows a code example on how to use this model
+Below shows a code example on how to use this model via Alpaca prompt
 
 ```python
 import torch