This model is a version of Meta-Llama-3-8B that has been fine-tuned with Our In House CustomData.

Train Spec : We utilized an A100x8 * 1 for training our model with DeepSpeed / HuggingFace TRL Trainer / HuggingFace Accelerate

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Alphacode-AI/Alphallama3-8B_v2

Base model

Finetuned

(471)

this model

Quantizations

Spaces using Alphacode-AI/Alphallama3-8B_v2 7