We finetuned Llama2-7B on Code-Alpaca-Instruct Dataset (sahil2801/CodeAlpaca-20k) for 5 epochs or ~ 25,000 steps using
MonsterAPI
no-code
LLM finetuner
.
This dataset is HuggingFaceH4/CodeAlpaca_20K unfiltered, removing 36 instances of blatant alignment.
The finetuning session got completed in 4 hours and costed us only
$16
for the entire finetuning run!
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%
Gradient accumulation steps: 1
Loss metrics:
license: apache-2.0
Runs of monsterapi CodeAlpaca_LLAMA2_7B on huggingface.co
5
Total runs
0
24-hour runs
-2
3-day runs
2
7-day runs
-7
30-day runs
More Information About CodeAlpaca_LLAMA2_7B huggingface.co Model
CodeAlpaca_LLAMA2_7B huggingface.co
CodeAlpaca_LLAMA2_7B huggingface.co is an AI model on huggingface.co that provides CodeAlpaca_LLAMA2_7B's model effect (), which can be used instantly with this monsterapi CodeAlpaca_LLAMA2_7B model. huggingface.co supports a free trial of the CodeAlpaca_LLAMA2_7B model, and also provides paid use of the CodeAlpaca_LLAMA2_7B. Support call CodeAlpaca_LLAMA2_7B model through api, including Node.js, Python, http.
CodeAlpaca_LLAMA2_7B huggingface.co is an online trial and call api platform, which integrates CodeAlpaca_LLAMA2_7B's modeling effects, including api services, and provides a free online trial of CodeAlpaca_LLAMA2_7B, you can try CodeAlpaca_LLAMA2_7B online for free by clicking the link below.
monsterapi CodeAlpaca_LLAMA2_7B online free url in huggingface.co:
CodeAlpaca_LLAMA2_7B is an open source model from GitHub that offers a free installation service, and any user can find CodeAlpaca_LLAMA2_7B on GitHub to install. At the same time, huggingface.co provides the effect of CodeAlpaca_LLAMA2_7B install, users can directly use CodeAlpaca_LLAMA2_7B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
CodeAlpaca_LLAMA2_7B install url in huggingface.co: