File size: 3,583 Bytes
8e41106 3fea421 8e41106 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
---
license: llama3.2
language:
- en
pipeline_tag: text-generation
tags:
- nlp
---
# Llama-3.2-1B-Tele-it Model Card
## Model Summary
The language model Llama-3.2-1B-Tele-it is an instruct version of [Llama-3.2-1B-Tele](https://huggingface.co/AliMaatouk/Llama-3.2-1B-Tele), which is based on Meta [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) and specialized in telecommunications. It was fine-tuned to follow instructions using Supervised Fine-tuning (SFT) with a combination of the [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) and [Open-instruct](https://huggingface.co/datasets/VMware/open-instruct) datasets.
### Context Length
The context length of the model is 8192 tokens.
## Usage
Llama-3.2-1B-Tele-it has been fine-tuned using pairs of instructions and responses from the [Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) and [Open-instruct](https://huggingface.co/datasets/VMware/open-instruct) datasets, separated by the "\n" delimiter. Below is an example of how to query the model using this format:
```markdown
Prompt: Explain to me Shannon capacity.\n
Model: The Shannon capacity is a measure of the maximum amount of information that can be transmitted through a communication channel over a given time period. It is a measure of the channel capacity that takes into account the signal-to-noise ratio (SNR) of the channel and the channel's bandwidth.
The formula for the Shannon capacity of a communication channel is:
C = log2(1 + SNR)
Where:
C = Shannon capacity
SNR = Signal-to-Noise Ratio
```
## Sample Code
Below we share some code snippets on how to get quickly started with running the model. First, make sure to `pip install transformers`, then copy the snippet corresponding to your hardware and adapt it to your usecase.
#### Running the model on a CPU
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AliMaatouk/Llama-3.2-1B-Tele-it", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Llama-3.2-1B-Tele-it")
prompt = "Explain to me Shannon capacity.\n"
input_ids = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**input_ids, max_new_tokens=100)
generated_tokens = outputs[0, len(input_ids['input_ids'][0]):]
response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(response)
```
#### Running the model on a single / multi GPU
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("AliMaatouk/Llama-3.2-1B-Tele-it", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Llama-3.2-1B-Tele-it")
prompt = "Explain to me Shannon capacity.\n"
input_ids = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**input_ids, max_new_tokens=100)
generated_tokens = outputs[0, len(input_ids['input_ids'][0]):]
response = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(response)
```
## Citation
You can find the paper with all details about the model at https://arxiv.org/abs/2409.05314. Please cite it as follows:
```bib
@misc{maatouk2024telellmsseriesspecializedlarge,
title={Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications},
author={Ali Maatouk and Kenny Chirino Ampudia and Rex Ying and Leandros Tassiulas},
year={2024},
eprint={2409.05314},
archivePrefix={arXiv},
primaryClass={cs.IT},
url={https://arxiv.org/abs/2409.05314},
}
```
|