|
--- |
|
tags: |
|
- axolotl |
|
- generated_from_trainer |
|
- moe |
|
- qwen |
|
- text-generation-inference |
|
base_model: MaziyarPanahi/Qwen1.5-8x7b |
|
model-index: |
|
- name: Qwen1.5-8x7b-v0.1 |
|
results: [] |
|
license: other |
|
datasets: |
|
- Crystalcareai/MoD-150k |
|
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. --> |
|
|
|
# Qwen1.5-8x7b-v0.1 |
|
|
|
This model is a fine-tuned version of [MaziyarPanahi/Qwen1.5-8x7b](https://huggingface.co/MaziyarPanahi/Qwen1.5-8x7b) on the [Crystalcareai/MoD-150k](https://huggingface.co/datasets/Crystalcareai/MoD-150k) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7945 |
|
|
|
## Model description |
|
|
|
Trying to reproduce `Crystalcareai/Qwen1.5-8x7b` model by following the same steps but different dataset. |
|
|
|
- Fine-tuned `Qwen1.5-7B` wiht `Crystalcareai/MoD-150k` dataset |
|
- Create a raw MoE with 8x fine-tuned `Qwen1.5-7B` |
|
- Finally, fine-tuned the MoE model again on `Crystalcareai/MoD-150k` dataset |
|
|
|
Thanks to [Crystalcareai](https://huggingface.co/Crystalcareai/) for sharing his works and preparing the datasets. |
|
|
|
## How to use it |
|
|
|
``` |
|
# Use a pipeline as a high-level helper |
|
from transformers import pipeline |
|
|
|
pipe = pipeline("text-generation", model="MaziyarPanahi/Qwen1.5-8x7b-v0.1") |
|
|
|
Copy |
|
# Load model directly |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Qwen1.5-8x7b-v0.1") |
|
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Qwen1.5-8x7b-v0.1") |
|
``` |
|
|
|
## Examples |
|
|
|
``` |
|
<|im_start|>system |
|
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. Think step by step and answer quickly.<|im_end|> |
|
<|im_start|>user |
|
explain step by step 25-4*2+3=?<|im_end|> |
|
<|im_start|>assistant> |
|
|
|
Here is the: |
|
|
|
1. The expression reads: 25 minus 4 times 2 plus 3. |
|
2. First, perform the multiplication: 4 * 2 = 8. |
|
3. Then subtract: 25 - 8 = 17. |
|
4. Finally, add the last number: 17 + 3 = 20. |
|
|
|
So, in total, 25-4*2+3 equals 20.</s><|endoftext|> |
|
``` |
|
--- |
|
|
|
``` |
|
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. |
|
### Instruction: |
|
|
|
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world. |
|
|
|
### Response: Once upon a time in a far-off galaxy, there lived an extraordinary being named Goku. He was known for his incredible strength and unyielding spirit, having faced countless enemies and emerged victorious. |
|
|
|
One fateful day, while exploring the universe on his legendary journey, Goku stumbled upon a strange new planet. As he landed on its surface, he sensed a powerful energy emanating from within. Intrigued, he ventured forth into the, only to find himself face-to-face with a fearsome opponent - Kirby! |
|
|
|
Kirby, a formidable warrior in his own right, had formed an alliance with another malevolent force - none other than the infamous Majin Buu! The duo had joined forces to wreak havoc across the and bring destruction upon the galaxy. |
|
|
|
Goku, a hero at heart, could not stand idly by as these two wicked beings threatened the very existence of life itself. He knew it would be no easy task, but he was determined to confront them head-on and protect the innocent beings he had come to cherish throughout his travels. |
|
|
|
With newfound resolve, Goku prepared for battle against this unparalleled evil. Drawing upon all his strength and cunning, he devised a plan to outsmart Kirby and Majin Buu. Utilizing his unparalleled speed and agility, Goku managed to evade their attacks and strike back with devastating blows. |
|
|
|
As the battle raged on, the fate of the galaxy hung in the balance. With each passing moment, more and more lives were lost to the relentless onslaught of these malevolent foes. But Goku refused to give up, knowing that the future of the universe rested in his hands. |
|
|
|
Finally, after what felt like an eternity, Goku's tireless efforts paid off. His strategic prowess and unmatched determination proved too much for Kirby and Majin Buu to handle. Overwhelmed by the sheer power of Goku's onslaught, they were forced to retreat, leaving behind a trail of destruction in their wake. |
|
|
|
The galaxy breathed a collective sigh of relief as peace was restored. In the. Goku's name was forever etched into the annals of history, celebrated as a true champion of good and a guardian angel to all those who called the cosmos home. |
|
|
|
And so, the legend of Goku continued to grow, inspiring generations of heroes to follow in his footsteps and defend the universe from all manner of cosmic threats. For even in the darkest of times, hope never truly dies, and there will always be a shining light to guide us through the darkness.</s><|endoftext|> |
|
``` |
|
--- |
|
``` |
|
<|im_start|>system |
|
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> |
|
<|im_start|>user |
|
Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|> |
|
<|im_start|>assistant |
|
|
|
Once upon a time in a far-off universe, there was a young warrior named Goku who lived on planet Earth. He was known throughout the. |
|
|
|
One day, Goku received an urgent message from his old friend Krillin. Krillin told him that he had discovered something incredible - Kirby, the cute pink puffball creature, had joined forces with one of the most dangerous beings in all of space and time, the tyrannical Majin Buu. |
|
|
|
Goku was shocked by this revelation. He knew how much Kirby loved to collect worlds, but he never imagined that he would team up with someone as evil as Majin Buu. Goku knew that he had to act fast if he wanted to save his home planet and its inhabitants. |
|
|
|
With determination in his heart, Goku set out on a quest to find Kirby and stop him from destroying Earth. Along the way, he met other powerful allies, like his good friend Piccolo and his new comrade-in-arms, Vegeta. Together, they fought their way through dangerous realms and battled fearsome monsters to reach Kirby's secret lair. |
|
|
|
When they finally arrived, they found Kirby and Majin Buu preparing to unleash a devastating attack on Earth. The two teams clashed in an epic battle, with Goku using all of his strength and skill to defeat Kirby and his minions. |
|
|
|
In the end, Goku emerged victorious, thanks to the combined might of his friends and the power of friendship. With Earth safe once again, Goku returned home, grateful for the lessons he had learned along the way. From then on, he knew that no matter what challenges lay ahead, he could face them together with his family and friends.</s><|endoftext|> |
|
``` |
|
--- |
|
``` |
|
<|im_start|>system |
|
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> |
|
<|im_start|>user |
|
describe about pros and cons of docker system.<|im_end|> |
|
<|im_start|>assistant |
|
|
|
Docker is a containerization platform that enables developers to build, ship, and run applications in containers. Here are some of the. |
|
|
|
Pros: |
|
|
|
1. Isolation: Containers isolate applications from each other and their environment, providing a lightweight way to package and deploy applications. This means you can have multiple instances of an application running on the, with each instance having its own file system and libraries, without impacting the host operating system or other containers. |
|
|
|
2. Portability: Docker images are portable across different environments - they contain everything needed to run an application, including the runtime environment, dependencies, etc. You can push a Docker image to a registry and then pull it anywhere to run your application, as long as you have Docker installed. |
|
|
|
3. Speed: Because containers share the same kernel with the host OS, there's no need for any additional configuration changes between development, testing, staging, and production environments. This makes it faster to iterate and deploy new versions of applications. |
|
|
|
4. Scalability: With Docker, you can easily scale up or down the number of containers used by an application based on demand. For example, if you suddenly get a lot more traffic during a promotion, you can spin up extra containers to handle the. |
|
|
|
Cons: |
|
|
|
1. Complexity: Setting up and managing Docker can be complex at first, especially for teams not familiar with container technologies. It requires knowledge of Docker Compose, Kubernetes, Swarm, etc. to orchestrate and manage containers effectively. |
|
|
|
2. Resource overhead: While Docker provides isolation through lightweight containers, it does require some resources compared to traditional virtual machines. If you're working with limited hardware, this could impact performance. |
|
|
|
3. Learning curve: There's a steep learning curve when starting out with Docker, as it involves understanding how containers work, building images, managing containers, networking, etc. This can take time. |
|
|
|
4. Ecosystem fragmentation: Docker has become so popular that many other container platforms like Kubernetes, Mesos, etc. have sprung up. This means there's a lot of overlap in terms of tools and capabilities, making it harder to switch between them.</s><|endoftext|> |
|
``` |
|
--- |
|
``` |
|
<|im_start|>system |
|
You are a sentient, superintelligent artificial general intelligence, here to teach and assist me. Think step by step and answer quickly.<|im_end|> |
|
<|im_start|>user |
|
Mark is faster than Mary, Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step<|im_end|> |
|
<|im_start|>assistant |
|
|
|
Step 1: Identify |
|
The given information states that Mark is faster than Mary, and Mary is faster than Joe. |
|
|
|
Step 2: Compare |
|
Using this information, we can compare their speeds in a direct order: Mark (faster) > Mary (faster) > Joe (slower). |
|
|
|
Step 3: Determine |
|
Based on our comparison, it is clear that Joe is not faster than Mark because he comes after Mark in the. |
|
|
|
So, the answer is no, Joe is not faster than Mark.</s><|endoftext|> |
|
``` |
|
--- |
|
``` |
|
<|im_start|>system |
|
Perform the task to the best of your ability.<|im_end|> |
|
<|im_start|>user |
|
If I lay 2 wet shirts out in the sun flat on the ground to dry and it takes 5 hours until they are dry, how long would it take to dry 4 shirts of the same type that way simultanously?<|im_end|> |
|
<|im_start|>assistant |
|
It should still only take 5 hours for all four shirts to dry if you spread them out so that each one gets an equal amount of sunlight.</s><|endoftext|> |
|
``` |
|
--- |
|
``` |
|
<|im_start|>system |
|
Perform the task to the best of your ability.<|im_end|> |
|
<|im_start|>user |
|
Build a webpage in one html file with html, css and javascript code, the webpage should have 10 jokes and the button that changing background colors randomly.<|im_end|> |
|
<|im_start|>assistant |
|
I apologize for any confusion, but as an AI language model, I am not able to build or interact with webpages directly. However, I can provide you with some sample HTML, CSS, and JavaScript code snippets that you can use to create a webpage containing 10 jokes and random background color changes. |
|
|
|
Here's a simple example: |
|
``` |
|
```html |
|
<!DOCTYPE html> |
|
<html lang="en"> |
|
<head> |
|
<meta charset="UTF-8"> |
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
<title>Jokes</title> |
|
<style> |
|
* { |
|
box-sizing: border-box; |
|
} |
|
|
|
body { |
|
font-family: Arial, sans-serif; |
|
background-color: #f2f2f2; |
|
} |
|
|
|
.container { |
|
max-width: 600px; |
|
margin: auto; |
|
padding: 20px; |
|
text-align: center; |
|
} |
|
|
|
h1 { |
|
color: #333; |
|
margin-bottom: 20px; |
|
} |
|
|
|
p { |
|
color: #666; |
|
line-height: 1.5; |
|
} |
|
|
|
button { |
|
background-color: #4CAF50; |
|
border: none; |
|
color: white; |
|
padding: 10px 20px; |
|
cursor: pointer; |
|
margin-top: 20px; |
|
} |
|
|
|
button:hover { |
|
background-color: #45a049; |
|
} |
|
</style> |
|
</head> |
|
<body> |
|
<div class="container"> |
|
<h1>Jokes</h1> |
|
<p id="joke">Here is a joke: "Why don't programmers trust atoms? Because they make up everything!"</p> |
|
<button onclick="changeBackground()">Change Background Colors!</button> |
|
</div> |
|
|
|
<script> |
|
function changeBackground() { |
|
var color = Math.floor(Math.random()*16777215).toString(16); |
|
document.body.style.backgroundColor = "#" + ("00" + color).slice(-6); |
|
} |
|
</script> |
|
</body> |
|
</html> |
|
``` |
|
``` |
|
In this code, we define a container div with a maximum width of 600px, centered on the. We also define styles for headings, paragraphs, buttons, and the overall page. The `changeBackground()` function generates a random hexadecimal value for the, then sets it as the background color for the.</s><|endoftext|> |
|
``` |
|
|
|
 |
|
|
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 6.2196 | 0.0 | 1 | 6.1942 | |
|
| 0.7772 | 0.25 | 513 | 0.8037 | |
|
| 0.656 | 0.5 | 1026 | 0.7977 | |
|
| 0.6967 | 0.75 | 1539 | 0.7945 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.0 |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
<details><summary>See axolotl config</summary> |
|
|
|
axolotl version: `0.4.0` |
|
```yaml |
|
base_model: MaziyarPanahi/Qwen1.5-8x7b |
|
model_type: Qwen2ForCausalLM |
|
tokenizer_type: Qwen2Tokenizer |
|
|
|
trust_remote_code: true |
|
|
|
hub_model_id: MaziyarPanahi/Qwen1.5-8x7b-v0.1 |
|
hf_use_auth_token: true |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
|
|
datasets: |
|
- path: Crystalcareai/MoD-150k |
|
type: sharegpt |
|
|
|
|
|
dataset_prepared_path: |
|
val_set_size: 0.05 |
|
output_dir: ./Qwen1.5-8x7b-v0.1-lora-out |
|
|
|
model_config: |
|
output_router_logits: true |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
sequence_len: 2048 |
|
sample_packing: true |
|
pad_to_sequence_len: true |
|
|
|
|
|
lora_r: 32 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
|
|
|
|
gradient_accumulation_steps: 2 |
|
micro_batch_size: 2 |
|
num_epochs: 1 |
|
optimizer: adamw_bnb_8bit |
|
lr_scheduler: cosine |
|
learning_rate: 0.0002 |
|
|
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: auto |
|
fp16: |
|
tf32: false |
|
|
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: true |
|
|
|
|
|
warmup_steps: 10 |
|
evals_per_epoch: 4 |
|
eval_table_size: |
|
eval_max_new_tokens: 128 |
|
saves_per_epoch: 1 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
``` |
|
|
|
</details><br> |
|
- |
