thrunlab_-_sparse_llama_7b_hf_refined_web_70p_2024-03-25-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

sparse_llama_7b_hf_refined_web_70p_2024-03-25 - bnb 4bits

• Model creator: https://huggingface.co/thrunlab/
• Original model: https://huggingface.co/thrunlab/sparse_llama_7b_hf_refined_web_70p_2024-03-25/

Original model description:

base_model: meta-llama/Llama-2-7b-hf tags:

• generated_from_trainer model-index:
• name: sparse_llama_7b_hf_refined_web_70p_2024-03-25 results: []

---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

sparse_llama_7b_hf_refined_web_70p_2024-03-25

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1856

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 0
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• total_eval_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.2