Jaward
/

CodeOptimus-Instruct-Mistral-7B-v0.1.gguf

Inference Endpoints

Model card Files Files and versions

Jaward commited on May 17

Commit

2097435

•

1 Parent(s): 712daeb

Update README.md

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -5,10 +5,11 @@ license: mit
 ### Model Name: CodeOptimus - Supervised Instruction Fine-tuning [Mistral 7B Instruct](https://mistral.ai/news/announcing-mistral-7b/) using qLora.
 ## Prerequisites For Reproduction
-1. **GPU**: Requires powerful GPUs, such as the A100.
-2. **Python Packages**: Install requirements.txt.
-3. **Dataset**: Download [code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) plus some custom curated dataset
-4. **Mistra-7B-Instruct-v0.1**: Download [mistralai/Mistral-7B-Instruct-v0.1 ](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) pytorch bin weights
 ## Samples showing Adaptive Learning Capabilities

 ### Model Name: CodeOptimus - Supervised Instruction Fine-tuning [Mistral 7B Instruct](https://mistral.ai/news/announcing-mistral-7b/) using qLora.
 ## Prerequisites For Reproduction
+1. **GPU**: Requires powerful GPUs - I used 7 Nvidia A100s.
+2. **Train Time**: 1 week.
+3. **Python Packages**: Install requirements.txt.
+4. **Dataset**: Download [code_instructions_122k_alpaca_style](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) plus some custom curated dataset
+5. **Mistra-7B-Instruct-v0.1**: Download [mistralai/Mistral-7B-Instruct-v0.1 ](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) pytorch bin weights
 ## Samples showing Adaptive Learning Capabilities