dellaanima
/

llama2_7b_hf_LoRA_FT_merged_seq_len_256_wikitext2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Edit model card

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Model Performance

Validation Loss: 1.829
Validation Perplexity: 6.584

Model Configuration

LoRA FT: Applied to self_attn.q_proj and self_attn.v_proj, Rank = 16
Epochs: 3
Learning Rate: 0.00001
Batch Size: 8
Sequence Length: 256

Downloads last month: 3

Safetensors

Model size

6.74B params

Tensor type

F32

·