Update README.md

README.md

@@ -10,7 +10,7 @@ pipeline_tag: text-generation
 base_model: meta-llama/Llama-2-70b-hf
 ---
 
-# llama-2-70b-dolphin 🦙🐬
+# llama-2-70b-instruct-v0.1 🦙🐬
 
 This instruction model was built via parameter-efficient QLoRA finetuning of [llama-2-70b](https://huggingface.co/meta-llama/Llama-2-70b-hf) on the first 25k rows of [ehartford/dolphin](https://huggingface.co/datasets/ehartford/dolphin) (an open-source implementation of [Microsoft's Orca](https://www.microsoft.com/en-us/research/publication/orca-progressive-learning-from-complex-explanation-traces-of-gpt-4/)). Finetuning was executed on a single H100 (80 GB PCIe) for roughly 17 hours on the [Lambda Labs](https://cloud.lambdalabs.com/instances) platform.
 
@@ -30,13 +30,13 @@ We use state-of-the-art [Language Model Evaluation Harness](https://github.com/E
 
 * Model license: Llama 2 Community License Agreement
 * Basic usage: [notebook](assets/basic_inference_llama_2_dolphin.ipynb)
-* Finetuning code: [script](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/llama-2/dolphin/sft-llama-2-70b-dolphin-peft.py)
-* Loss curves: [plot](https://huggingface.co/dfurman/llama-2-70b-dolphin-peft#finetuning-description)
-* Runtime stats: [table](https://huggingface.co/dfurman/llama-2-70b-dolphin-peft#runtime-tests)
+* Finetuning code: [script](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/llama-2/dolphin/sft-llama-2-70b-instruct-v0.1-peft.py)
+* Loss curves: [plot](https://huggingface.co/dfurman/llama-2-70b-instruct-v0.1-peft#finetuning-description)
+* Runtime stats: [table](https://huggingface.co/dfurman/llama-2-70b-instruct-v0.1-peft#runtime-tests)
 
 ## Loss curve
 
-![loss curves](https://raw.githubusercontent.com/daniel-furman/sft-demos/main/assets/jul_24_23_1_14_00_log_loss_curves_llama-2-70b-dolphin.png)
+![loss curves](https://raw.githubusercontent.com/daniel-furman/sft-demos/main/assets/jul_24_23_1_14_00_log_loss_curves_llama-2-70b-instruct-v0.1.png)
 
 The above loss curve was generated from the run's private wandb.ai log.  
 
@@ -47,7 +47,7 @@ Example 1:
 **User**:
 > You are a helpful assistant. Write me a numbered list of things to do in New York City.\n
 
-**llama-2-70b-dolphin-peft**:
+**llama-2-70b-instruct-v0.1-peft**:
 > 1. Visit the Statue of Liberty: Take a ferry to Liberty Island and see the iconic symbol of freedom and democracy.
 > 2. Explore Central Park: Enjoy the lush greenery, take a stroll, or rent a bike to explore the park's many attractions, such as the Central Park Zoo and Strawberry Fields.
 > 3. Visit the Empire State Building: Take an elevator to the observation deck for breathtaking views of the city.
@@ -65,7 +65,7 @@ Example 2:
 
 > You are a helpful assistant. Write a short email inviting my friends to a dinner party on Friday. Respond succinctly.\n
 
-**llama-2-70b-dolphin-peft**:
+**llama-2-70b-instruct-v0.1-peft**:
 
 > Subject: Dinner Party Invitation - Friday, 7 PM
 > 
@@ -88,7 +88,7 @@ Example 3:
 
 > You are a helpful assistant. Tell me a recipe for vegan banana bread.\n
 
-**llama-2-70b-dolphin-peft**:
+**llama-2-70b-instruct-v0.1-peft**:
 
 > Sure! Here's a delicious and easy vegan banana bread recipe:
 > 
@@ -227,7 +227,7 @@ print(tokenizer.decode(output["sequences"][0], skip_special_tokens=True))
 |:-----------------------------:|:----------------------:|:---------------------:|:-------------:|:-----------------------:|
 | 4.50                        | 1x H100 (80 GB PCIe)  | torch               | nf4    | 39                    |
 
-The above runtime stats were generated from this [notebook](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/llama-2/dolphin/postprocessing-llama-2-70b-dolphin-peft.ipynb). 
+The above runtime stats were generated from this [notebook](https://github.com/daniel-furman/sft-demos/blob/main/src/sft/one_gpu/llama-2/dolphin/postprocessing-llama-2-70b-instruct-v0.1-peft.ipynb). 
 
 ## Acknowledgements