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-Tele - GGUF - Model creator: https://huggingface.co/AliMaatouk/ - Original model: https://huggingface.co/AliMaatouk/Phi-1.5-Tele/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Phi-1.5-Tele.Q2_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q2_K.gguf) | Q2_K | 0.54GB | | [Phi-1.5-Tele.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.IQ3_XS.gguf) | IQ3_XS | 0.59GB | | [Phi-1.5-Tele.IQ3_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.IQ3_S.gguf) | IQ3_S | 0.61GB | | [Phi-1.5-Tele.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q3_K_S.gguf) | Q3_K_S | 0.61GB | | [Phi-1.5-Tele.IQ3_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.IQ3_M.gguf) | IQ3_M | 0.64GB | | [Phi-1.5-Tele.Q3_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q3_K.gguf) | Q3_K | 0.69GB | | [Phi-1.5-Tele.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q3_K_M.gguf) | Q3_K_M | 0.69GB | | [Phi-1.5-Tele.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q3_K_L.gguf) | Q3_K_L | 0.75GB | | [Phi-1.5-Tele.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.IQ4_XS.gguf) | IQ4_XS | 0.74GB | | [Phi-1.5-Tele.Q4_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q4_0.gguf) | Q4_0 | 0.77GB | | [Phi-1.5-Tele.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.IQ4_NL.gguf) | IQ4_NL | 0.78GB | | [Phi-1.5-Tele.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q4_K_S.gguf) | Q4_K_S | 0.78GB | | [Phi-1.5-Tele.Q4_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q4_K.gguf) | Q4_K | 0.83GB | | [Phi-1.5-Tele.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q4_K_M.gguf) | Q4_K_M | 0.83GB | | [Phi-1.5-Tele.Q4_1.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q4_1.gguf) | Q4_1 | 0.85GB | | [Phi-1.5-Tele.Q5_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q5_0.gguf) | Q5_0 | 0.92GB | | [Phi-1.5-Tele.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q5_K_S.gguf) | Q5_K_S | 0.92GB | | [Phi-1.5-Tele.Q5_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q5_K.gguf) | Q5_K | 0.96GB | | [Phi-1.5-Tele.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q5_K_M.gguf) | Q5_K_M | 0.96GB | | [Phi-1.5-Tele.Q5_1.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q5_1.gguf) | Q5_1 | 1.0GB | | [Phi-1.5-Tele.Q6_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q6_K.gguf) | Q6_K | 1.09GB | | [Phi-1.5-Tele.Q8_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Phi-1.5-Tele-gguf/blob/main/Phi-1.5-Tele.Q8_0.gguf) | Q8_0 | 1.41GB | Original model description: --- license: mit language: - en pipeline_tag: text-generation tags: - nlp --- # Phi-1.5-Tele Model Card ## Model Summary The language model Phi-1.5-Tele is a Transformer with **1.3 billion** parameters, specialized in telecommunications. It is based on Microsoft [phi-1.5](https://huggingface.co/microsoft/phi-1_5) and was continutally pretrained on [Tele-Data](https://huggingface.co/datasets/AliMaatouk/Tele-Data), a large-scale dataset of approximately 2.5 billion tokens of telecommunications material, including articles, standards, and general web content related to the telecommunications domain. When assessed against telecommunications benchmarks such as [Tele-Eval](https://huggingface.co/datasets/AliMaatouk/Tele-Eval), Phi-1.5-Tele outperforms [phi-1.5](https://huggingface.co/microsoft/phi-1_5) by several percentage points. Additionally, Phi-1.5-Tele matches [phi-1.5](https://huggingface.co/microsoft/phi-1_5) across benchmarks related to common sense, language understanding, and logical reasoning. Thus, this adaptation was achieved with minimal compromise in performance on the original version. ### Context Length The model was trained on a context length of 2048 tokens. ## Usage Phi-1.5-Tele is a base model best suited for fine-tuning on applications related to telecommunications. Although it has not been specifically fine-tuned to follow instructions, it can be prompted to answer questions and follow instructions using the following format: ```markdown Write me a poem about telecommunications. Answer: Our world is a network of digital streams, Connecting every voice and thought, Through the wires and fibers that transmit, Bringing us closer to the end of the road. ``` where the model generates the text after "Answer:". ## 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/Phi-1.5-Tele", torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Phi-1.5-Tele") prompt = "Write me a poem about telecommunications.\nAnswer:" 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/Phi-1.5-Tele", torch_dtype="auto", device_map="auto") tokenizer = AutoTokenizer.from_pretrained("AliMaatouk/Phi-1.5-Tele") prompt = "Write me a poem about telecommunications.\nAnswer:" 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}, } ```