|
Quantization made by Richard Erkhov. |
|
|
|
[Github](https://github.com/RichardErkhov) |
|
|
|
[Discord](https://discord.gg/pvy7H8DZMG) |
|
|
|
[Request more models](https://github.com/RichardErkhov/quant_request) |
|
|
|
|
|
phi-1_5_chat_128k - bnb 4bits |
|
- Model creator: https://huggingface.co/voidful/ |
|
- Original model: https://huggingface.co/voidful/phi-1_5_chat_128k/ |
|
|
|
|
|
|
|
|
|
Original model description: |
|
--- |
|
language: |
|
- en |
|
license: mit |
|
--- |
|
|
|
## Model Summary |
|
|
|
The language model Phi-1.5 is a Transformer with **1.3 billion** parameters. It was trained using the same data sources as [phi-1](https://huggingface.co/microsoft/phi-1), augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters. |
|
|
|
We've trained Microsoft Research's phi-1.5, 1.3B parameter model with multi-turn conversation datasets on at most 32k and extended to 128k. |
|
|
|
## Example |
|
```python |
|
import torch |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
torch.set_default_device("cuda") |
|
|
|
model = AutoModelForCausalLM.from_pretrained("voidful/phi-1_5_chat_32k") |
|
tokenizer = AutoTokenizer.from_pretrained("voidful/phi-1_5_chat_32k",device_map="auto") |
|
|
|
messages = [ |
|
{ |
|
"role": "system", |
|
"content": "You are a helpful assistant.", |
|
}, |
|
{"role": "user", "content": "how to make a keyboard?"}, |
|
{"role": "assistant", "content": """To make a keyboard, you will need the following materials: |
|
|
|
1. A set of keys, such as those found on a standard computer keyboard. |
|
2. A circuit board, such as a MOSFET (Metal-Oxide-Semiconductor-Fluorescent) board. |
|
3. A power supply to provide power to the circuit board. |
|
4. A case to enclose the circuit board and protect it from damage. |
|
5. A soldering iron and solder to connect the components together. |
|
|
|
Here is a basic outline of the steps involved in making a keyboard: |
|
|
|
1. Connect the circuit board to the power supply and the case. |
|
2. Connect the MOSFETs to the power supply and the case, using a soldering iron and solder. |
|
3. Connect the keys to the circuit board, using a soldering iron and solder. |
|
4. Test the keyboard to ensure that it works properly. |
|
5. Package the keyboard in a box or case for shipping or sale. |
|
|
|
Note that this is just a basic outline, and there are many additional steps and considerations that will depend on the specific design and requirements of your keyboard.</s>"""}, |
|
{"role": "user", "content": "where to buy the circuit?"}, |
|
] |
|
tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") |
|
|
|
outputs = model.generate(tokenized_chat, max_length=1024) |
|
text = tokenizer.batch_decode(outputs[:,tokenized_chat.shape[-1]:-1])[0] |
|
print(text) |
|
``` |
|
|
|
### Result |
|
``` |
|
There are several places where you can buy a circuit board. Here are some of the most common places: |
|
|
|
1. Electronics stores: Many electronics stores carry a variety of circuit boards for different purposes. |
|
2. Online marketplaces: There are several online marketplaces where you can buy circuit boards, such as Amazon, eBay, and Alibaba. |
|
3. Specialty stores: There are several specialty stores that carry a variety of circuit boards for different purposes, such as hobby stores, craft stores, and home improvement stores. |
|
|
|
In general, it is a good idea to shop around and compare prices and features before making a purchase. |
|
``` |
|
|
|
|