Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama-2-13b-hf-4bit-64rank - GGUF - Model creator: https://huggingface.co/LoftQ/ - Original model: https://huggingface.co/LoftQ/Llama-2-13b-hf-4bit-64rank/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Llama-2-13b-hf-4bit-64rank.Q2_K.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q2_K.gguf) | Q2_K | 4.52GB | | [Llama-2-13b-hf-4bit-64rank.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.IQ3_XS.gguf) | IQ3_XS | 4.99GB | | [Llama-2-13b-hf-4bit-64rank.IQ3_S.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.IQ3_S.gguf) | IQ3_S | 5.27GB | | [Llama-2-13b-hf-4bit-64rank.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q3_K_S.gguf) | Q3_K_S | 5.27GB | | [Llama-2-13b-hf-4bit-64rank.IQ3_M.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.IQ3_M.gguf) | IQ3_M | 5.57GB | | [Llama-2-13b-hf-4bit-64rank.Q3_K.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q3_K.gguf) | Q3_K | 5.9GB | | [Llama-2-13b-hf-4bit-64rank.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q3_K_M.gguf) | Q3_K_M | 5.9GB | | [Llama-2-13b-hf-4bit-64rank.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q3_K_L.gguf) | Q3_K_L | 6.45GB | | [Llama-2-13b-hf-4bit-64rank.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.IQ4_XS.gguf) | IQ4_XS | 6.54GB | | [Llama-2-13b-hf-4bit-64rank.Q4_0.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q4_0.gguf) | Q4_0 | 6.86GB | | [Llama-2-13b-hf-4bit-64rank.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.IQ4_NL.gguf) | IQ4_NL | 6.9GB | | [Llama-2-13b-hf-4bit-64rank.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q4_K_S.gguf) | Q4_K_S | 6.91GB | | [Llama-2-13b-hf-4bit-64rank.Q4_K.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q4_K.gguf) | Q4_K | 7.33GB | | [Llama-2-13b-hf-4bit-64rank.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q4_K_M.gguf) | Q4_K_M | 7.33GB | | [Llama-2-13b-hf-4bit-64rank.Q4_1.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q4_1.gguf) | Q4_1 | 7.61GB | | [Llama-2-13b-hf-4bit-64rank.Q5_0.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q5_0.gguf) | Q5_0 | 8.36GB | | [Llama-2-13b-hf-4bit-64rank.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q5_K_S.gguf) | Q5_K_S | 8.36GB | | [Llama-2-13b-hf-4bit-64rank.Q5_K.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q5_K.gguf) | Q5_K | 8.6GB | | [Llama-2-13b-hf-4bit-64rank.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q5_K_M.gguf) | Q5_K_M | 8.6GB | | [Llama-2-13b-hf-4bit-64rank.Q5_1.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q5_1.gguf) | Q5_1 | 9.1GB | | [Llama-2-13b-hf-4bit-64rank.Q6_K.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q6_K.gguf) | Q6_K | 9.95GB | | [Llama-2-13b-hf-4bit-64rank.Q8_0.gguf](https://huggingface.co/RichardErkhov/LoftQ_-_Llama-2-13b-hf-4bit-64rank-gguf/blob/main/Llama-2-13b-hf-4bit-64rank.Q8_0.gguf) | Q8_0 | 12.88GB | Original model description: --- license: mit language: - en pipeline_tag: text-generation tags: - 'quantization ' - lora --- # LoftQ Initialization | [Paper](https://arxiv.org/abs/2310.08659) | [Code](https://github.com/yxli2123/LoftQ) | [PEFT Example](https://github.com/huggingface/peft/tree/main/examples/loftq_finetuning) | LoftQ (LoRA-fine-tuning-aware Quantization) provides a quantized backbone Q and LoRA adapters A and B, given a full-precision pre-trained weight W. This model, `Llama-2-13b-hf-4bit-64rank`, is obtained from [LLAMA-2-13b](https://huggingface.co/meta-llama/Llama-2-13b-hf). The backbone is under `LoftQ/Llama-2-13b-hf-4bit-64rank` and LoRA adapters are under the `subfolder='loftq_init'`. ## Model Info ### Backbone - Stored format: `torch.bfloat16` - Size: ~ 26 GiB - Loaded format: bitsandbytes nf4 - Size loaded on GPU: ~6.5 GiB ### LoRA adapters - rank: 64 - lora_alpha: 64 - target_modules: ["down_proj", "up_proj", "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj"] ## Usage **Training** Here's an example of loading this model and preparing for the LoRA fine-tuning. ```python import torch from transformers import AutoModelForCausalLM, BitsAndBytesConfig from peft import PeftModel MODEL_ID = "LoftQ/Llama-2-13b-hf-4bit-64rank" base_model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, # you may change it with different models quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, # bfloat16 is recommended bnb_4bit_use_double_quant=False, bnb_4bit_quant_type='nf4', ), ) peft_model = PeftModel.from_pretrained( base_model, MODEL_ID, subfolder="loftq_init", is_trainable=True, ) # Do training with peft_model ... ``` ## Experiment Results We have conducted experiments on supervised fine-tuning of [GSM8K](https://huggingface.co/datasets/gsm8k) and [WikiText-2](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-raw-v1). | Model | Bits | Rank | LoRA Initial | GSM8K | WikiText-2 | | -------------- | ---- | ---- | -------------------- | ----- | ---------- | | LLAMA-2-13b | 16 | 64 | Gaussian + 0 | 45.3 | 5.12 | | LLAMA-2-13b | 4 | 64 | Gaussian + 0 (QLoRA) | 39.9 | 5.22 | | **LLAMA-2-13b** | 4 | 64 | LoftQ | 45.0 | 5.16 | **Inference** Here is an example code for inference after the model has been fine-tuned on [GSM8K](https://huggingface.co/datasets/gsm8k). ```python import torch from transformers import AutoModelForCausalLM, BitsAndBytesConfig from peft import PeftModel MODEL_ID = "LoftQ/Llama-2-13b-hf-4bit-64rank" base_model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.bfloat16, # you may change it with different models quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, # bfloat16 is recommended bnb_4bit_use_double_quant=False, bnb_4bit_quant_type='nf4', ), ) peft_model = PeftModel.from_pretrained( base_model, MODEL_ID, subfolder="gsm8k", is_trainable=True, ) # Do inference with peft_model ... ``` See the full code at our [Github Repo]((https://github.com/yxli2123/LoftQ)) ## Citation ```bibtex @article{li2023loftq, title={Loftq: Lora-fine-tuning-aware quantization for large language models}, author={Li, Yixiao and Yu, Yifan and Liang, Chen and He, Pengcheng and Karampatziakis, Nikos and Chen, Weizhu and Zhao, Tuo}, journal={arXiv preprint arXiv:2310.08659}, year={2023} } ```