README.md

---
license: other
datasets:
- c-s-ale/alpaca-gpt4-data
pipeline_tag: text2text-generation
---
<div style="width: 100%;">
    <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p><a href="https://discord.gg/UBgz4VXf">Chat & support: my new Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? Patreon coming soon!</a></p>
    </div>
</div>

## GPT4-Alpaca-LoRA_MLP-65B GGML

These files are the result of merging the [LoRA weights of chtan's gpt4-alpaca-lora_mlp-65B](https://huggingface.co/chtan/gpt4-alpaca-lora_mlp-65b) with the original Llama 65B model.

This repo contains 4bit and 5bit quantised GGML files for CPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).

## Repositories available

* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ)
* [4bit and 5bit GGML models for CPU inference in llama.cpp](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GGML)
* [float16 unquantised model for GPU inference and further conversions](https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-HF)

## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!

llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508

I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.

For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.

## Provided files
| Name | Quant method | Bits | Size | RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
`gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_0.bin` | q4_0 | 4bit | 40.8GB | 43GB | 4-bit. |
`gpt4-alpaca-lora_mlp-65B.ggmlv3.q4_1.bin` | q4_0 | 4bit | 44.9GB | 47GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
`gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_0.bin` | q5_0 | 5bit | 44.9GB | 47GB | 5-bit. Higher accuracy, higher resource usage and slower inference.  |
`gpt4-alpaca-lora_mlp-65B.ggmlv3.q5_1.bin` | q5_1 | 5bit | 49.0GB | 51GB | 5-bit. Even higher accuracy, higher resource usage and slower inference. |

Note: no q8_0 will be provided as HF won't allow uploading of files larger than 50GB :)

I am investigating other methods, eg a split ZIP file, and will try to upload this soon.

## Want to support my work?

I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.

So if you're able and willing to contribute, it'd be most gratefully received and will help me to keep providing models, and work on various AI projects.

Donaters will get priority support on any and all AI/LLM/model questions, and I'll gladly quantise any model you'd like to try.

* Patreon: coming soon! (just awaiting approval)
* Ko-Fi: https://ko-fi.com/TheBlokeAI
* Discord: https://discord.gg/UBgz4VXf
# Original model card

This repo provides the training checkpoint of LLaMA on the alpaca_data_gpt4 dataset via LoRA [MLP] on 8xA100(80G).

He et al. 2022 gave an insight that FFN can better utilize modification at larger capacities.

The codes is provided by [tloen/alpaca-lora: Instruct-tune LLaMA on consumer hardware (github.com)](https://github.com/tloen/alpaca-lora).

We modify the running scripts to
```bash
torchrun --nproc_per_node=8 finetune.py \
    --base_model '/cache1/chtan/large_models/llama-hf/llama-65b' \
    --data_path './alpaca_data_gpt4.json' \
    --output_dir './gpt4-alpaca-lora_mlp-65b' \
    --batch_size 128 \
    --micro_batch_size 2 \
    --num_epochs 10 \
    --learning_rate 1e-4 \
    --cutoff_len 512 \
    --val_set_size 2000 \
    --lora_r 16 \
    --lora_alpha 16 \
    --lora_dropout 0.05 \
    --lora_target_modules '[gate_proj,down_proj,up_proj]' \
    --train_on_inputs \
    --group_by_length
```

### Examples

**Instruction**: Tell me about alpacas.

**gpt4-alpaca-lora_mlp-65b**:

Alpacas are small, domesticated mammals that are closely related to llamas. They are native to the Andes Mountains of South America, primarily in Peru, Bolivia, and Chile. These animals have been domesticated for thousands of years and were used by the Incas for their fleece, meat, and as pack animals.

Alpacas are known for their soft and warm fleece, which comes in over 22 natural colors. Their fleece is highly valued and is used in the textile industry to make clothing and other products. Alpacas are also known for their friendly and gentle nature, making them popular pets and great additions to farms.

These animals are social and live in herds, typically with one dominant male. They communicate through a series of hums, clucks, and other vocalizations. Alpacas are also known for their distinctive "humming" sound, which they make when they are content or curious.

In terms of physical appearance, alpacas have a small, stocky build, with an average height of around 36 inches at the withers. They have large, expressive eyes, and their ears are perked forward. Alpacas are herbivores and primarily eat grasses and other vegetation. They are also known for their efficient digestive system, which allows them to thrive on a diet of low-quality forage.

Overall, alpacas are unique and fascinating animals that have been an important part of Andean culture for centuries. They continue to be valued for their fleece, meat, and as pets, and their popularity continues to grow around the world.

**Alpaca-LoRA**: Alpacas are members of the camelid family and are native to the Andes Mountains of South America. They are known for their soft, luxurious fleece, which is used to make clothing, blankets, and other items. Alpacas are herbivores and graze on grasses and other plants. They are social animals and live in herds of up to 20 individuals.

**Stanford Alpaca**: Alpacas are small, fluffy animals related to camels and llamas. They are native to Peru and Bolivia, and were first domesticated around 5,000 years ago. They are kept mainly for their fine, soft fleece, which is used to make knitwear and other garments. Alpacas are herd animals and live in small family groups, led by an older male. They are highly social animals and can form strong bonds with their owners.

**text-davinci-003**: Alpacas are a domesticated species of South American camelid, similar to llamas. They are native to the Andes Mountains in South America and are kept as livestock for their soft, luxurious wool. Alpacas are social animals and live in herds of up to 20 individuals. They are typically kept in small herds of two to five animals, and are relatively easy to care for. Alpacas are herbivores and feed on grass, hay, and other vegetation. They are also known for their gentle and friendly nature, making them popular as pets.

---

**Instruction**: Write a Python program that prints the first 10 Fibonacci numbers.

**gpt4-alpaca-lora_mlp-65b**:

Here is a Python program that prints the first 10 Fibonacci numbers:

```python
# initialize variables
a = 0
b = 1

# loop to print the first 10 Fibonacci numbers
for i in range(10):
    print(a, end=" ")
    a, b = b, a + b
```

In this program, we initialize two variables `a` and `b` with the first two Fibonacci numbers, which are 0 and 1. Then, we use a for loop to iterate 10 times. In each iteration, we print the current value of `a` and update the values of `a` and `b` using the formula `a = b` and `b = a + b`. This formula is the definition of the Fibonacci sequence.

**Alpaca-LoRA**:

```python
def fibonacci(n):
    if n == 0:
        return 0
    elif n == 1:
        return 1
    else:
        return fibonacci(n-1) + fibonacci(n-2)

print(fibonacci(10))
```

**Stanford Alpaca**:

```python
numbers = [0, 1]

for i in range(2, 11):
    numbers.append(numbers[i-2] + numbers[i-1])

print(numbers)
# Output: [0, 1, 1, 2, 3, 5, 8, 13, 21, 34]
```

**text-davinci-003**:

```python
# Fibonacci numbers are the numbers in the following integer sequence, called the Fibonacci sequence, and characterized by the fact that every number after the first two is the sum of the two preceding ones.

# Fibonacci sequence: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...

# Program:

# Initialize the first two numbers of the Fibonacci sequence
a = 0
b = 1

# Print the first 10 numbers of the Fibonacci sequence
print(a)
print(b)

for i in range(2,10):
    c = a + b
    a = b
    b = c
    print(c)
```

---

> [1] Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig: Towards a Unified View of Parameter-Efficient Transfer Learning. ICLR 2022