monsterapi
/

CodeAlpaca_LLAMA2_7B

alpaca-instruct

Model card Files Files and versions Community

Zangs3011 commited on Jul 31, 2023

Commit

1f7a648

•

1 Parent(s): 04cef71

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 datasets:
-- ewof/code-alpaca-instruct-unfiltered
 library_name: peft
 tags:
 - llama2-7b
@@ -14,7 +14,7 @@ tags:
 - gpt2
 ---
-We finetuned Llama2-7B on Code-Alpaca-Instruct Dataset (ewof/code-alpaca-instruct-unfiltered) for 5 epochs or ~ 25,000 steps using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
 This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.
@@ -22,7 +22,7 @@ The finetuning session got completed in 4  hours and costed us only `$16` for th
 #### Hyperparameters & Run details:
 - Model Path: meta-llama/Llama-2-7b
-- Dataset: ewof/code-alpaca-instruct-unfiltered
 - Learning rate: 0.0003
 - Number of epochs: 5
 - Data split: Training: 90% / Validation: 10%

 ---
 datasets:
+- sahil2801/CodeAlpaca-20k
 library_name: peft
 tags:
 - llama2-7b
 - gpt2
 ---
+We finetuned Llama2-7B on Code-Alpaca-Instruct Dataset (sahil2801/CodeAlpaca-20k) for 5 epochs or ~ 25,000 steps using [MonsterAPI](https://monsterapi.ai) no-code [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm).
 This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.
 #### Hyperparameters & Run details:
 - Model Path: meta-llama/Llama-2-7b
+- Dataset: sahil2801/CodeAlpaca-20k
 - Learning rate: 0.0003
 - Number of epochs: 5
 - Data split: Training: 90% / Validation: 10%