predibase
/

CodeLlama-7b-Instruct-hf-dequantized

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Edit model card

Uploaded model

Developed by: arnavgrg
License: apache-2.0
Finetuned from model : codellama/CodeLlama-7b-Instruct-hf

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 333

Safetensors

Model size

6.74B params

Tensor type

BF16

·

Finetuned from

Collection including predibase/CodeLlama-7b-Instruct-hf-dequantized

Dequantized Base Models

Dequantized (fp16) versions of nf4 quantized base models for faster inference. • 27 items • Updated 22 days ago • 1