Edit model card

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, 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

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.
Downloads last month
257
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for voidful/phi-1_5_chat_128k

Finetunes
7 models
Quantizations
1 model