---
license: llama2
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf
inference: false
model-index:
- name: llama2_70b_aqlm_toolcall
  results: []
datasets:
- vicgalle/alpaca-gpt4
- glaiveai/glaive-function-calling-v2
language:
- en
pipeline_tag: text-generation
---

<!-- 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. -->

# LLaMA-2 70B AQLM 2-bit QLoRA with function calling

This model is a fine-tuned version of [BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf](https://huggingface.co/BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf) using [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory).

The maximum GPU usage during training is **24GB**, and the model has preliminary conversation and tool-using abilities.

![examples](examples.png)

## Training and evaluation data

This model is fine-tuned using 1,000 examples of the Alpaca-GPT4 and Glaive-function-calling-v2 datasets, respectively.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from peft import PeftModel

tokenizer = AutoTokenizer.from_pretrained("hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling")
model = AutoModelForCausalLM.from_pretrained("BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf", torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, "hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs, streamer=streamer)
```

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
- mixed_precision_training: Native AMP

### Training results

![loss](train_loss.png)

### Framework versions

- PEFT 0.9.0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.2