richarderkhov/alimaatouk_-_gemma-2b-tele-it-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nGemma-2B-Tele-it - GGUF\n- Model creator: https://huggingface.co/AliMaatouk/\n- Original model: https://huggingface.co/AliMaatouk/Gemma-2B-Tele-it/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Gemma-2B-Tele-it.Q2_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q2_K.gguf) | Q2_K | 1.08GB |\n| [Gemma-2B-Tele-it.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q3_K_S.gguf) | Q3_K_S | 1.2GB |\n| [Gemma-2B-Tele-it.Q3_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q3_K.gguf) | Q3_K | 1.29GB |\n| [Gemma-2B-Tele-it.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q3_K_M.gguf) | Q3_K_M | 1.29GB |\n| [Gemma-2B-Tele-it.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q3_K_L.gguf) | Q3_K_L | 1.36GB |\n| [Gemma-2B-Tele-it.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.IQ4_XS.gguf) | IQ4_XS | 1.4GB |\n| [Gemma-2B-Tele-it.Q4_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q4_0.gguf) | Q4_0 | 1.44GB |\n| [Gemma-2B-Tele-it.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.IQ4_NL.gguf) | IQ4_NL | 1.45GB |\n| [Gemma-2B-Tele-it.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q4_K_S.gguf) | Q4_K_S | 1.45GB |\n| [Gemma-2B-Tele-it.Q4_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q4_K.gguf) | Q4_K | 1.52GB |\n| [Gemma-2B-Tele-it.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q4_K_M.gguf) | Q4_K_M | 1.52GB |\n| [Gemma-2B-Tele-it.Q4_1.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q4_1.gguf) | Q4_1 | 1.56GB |\n| [Gemma-2B-Tele-it.Q5_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q5_0.gguf) | Q5_0 | 1.68GB |\n| [Gemma-2B-Tele-it.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q5_K_S.gguf) | Q5_K_S | 1.68GB |\n| [Gemma-2B-Tele-it.Q5_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q5_K.gguf) | Q5_K | 1.71GB |\n| [Gemma-2B-Tele-it.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q5_K_M.gguf) | Q5_K_M | 1.71GB |\n| [Gemma-2B-Tele-it.Q5_1.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q5_1.gguf) | Q5_1 | 1.79GB |\n| [Gemma-2B-Tele-it.Q6_K.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q6_K.gguf) | Q6_K | 1.92GB |\n| [Gemma-2B-Tele-it.Q8_0.gguf](https://huggingface.co/RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf/blob/main/Gemma-2B-Tele-it.Q8_0.gguf) | Q8_0 | 2.49GB |\n\n\n\n\nOriginal model description:\n---\nlicense: gemma\nlanguage:\n- en\npipeline_tag: text-generation\ntags:\n- nlp\n---\n\n# Gemma-2B-Tele-it Model Card\n\n## Model Summary\n\nThe language model Gemma-2B-Tele-it is an instruct version of [Gemma-2B-Tele](https://huggingface.co/AliMaatouk/Gemma-2B-Tele), which is based on Google [gemma-2b](https://huggingface.co/google/gemma-2b) 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. \n\n### Context Length\n\nThe context length of the model is 8192 tokens.\n\n## Usage\n\nGemma-2B-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:\n\n```markdown\nPrompt: Explain to me Shannon capacity.\\n\n\nModel: Shannon capacity is a measure of the maximum achievable rate of reliable data transmission that can occur over a noisy channel, named after C. E. Shannon. It is also commonly known as channel capacity in information theory, and it is the largest amount of information that a channel can transmit reliably per unit of time. It is calculated by considering the noise and interference that a transmission may face.\n``` \n\n## Sample Code\n\nBelow 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.\n\n#### Running the model on a CPU\n\n\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\nmodel = AutoModelForCausalLM.from_pretrained(\"AliMaatouk/Gemma-2B-Tele-it\", torch_dtype=\"auto\")\ntokenizer = AutoTokenizer.from_pretrained(\"AliMaatouk/Gemma-2B-Tele-it\")\n\nprompt = \"Explain to me Shannon capacity.\\n\"\ninput_ids = tokenizer(prompt, return_tensors=\"pt\")\noutputs = model.generate(**input_ids, max_new_tokens=100)\n\ngenerated_tokens = outputs[0, len(input_ids['input_ids'][0]):]\nresponse = tokenizer.decode(generated_tokens, skip_special_tokens=True)\nprint(response)\n```\n\n#### Running the model on a single / multi GPU\n\n```python\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel = AutoModelForCausalLM.from_pretrained(\"AliMaatouk/Gemma-2B-Tele-it\", torch_dtype=\"auto\", device_map=\"auto\")\ntokenizer = AutoTokenizer.from_pretrained(\"AliMaatouk/Gemma-2B-Tele-it\")\n\nprompt = \"Explain to me Shannon capacity.\\n\"\ninput_ids = tokenizer(prompt, return_tensors=\"pt\").to(\"cuda\")\noutputs = model.generate(**input_ids, max_new_tokens=100)\n\ngenerated_tokens = outputs[0, len(input_ids['input_ids'][0]):]\nresponse = tokenizer.decode(generated_tokens, skip_special_tokens=True)\nprint(response)\n```\n\n## Citation\n\nYou can find the paper with all details about the model at https://arxiv.org/abs/2409.05314. Please cite it as follows:\n\n```bib\n@misc{maatouk2024telellmsseriesspecializedlarge,\n      title={Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications}, \n      author={Ali Maatouk and Kenny Chirino Ampudia and Rex Ying and Leandros Tassiulas},\n      year={2024},\n      eprint={2409.05314},\n      archivePrefix={arXiv},\n      primaryClass={cs.IT},\n      url={https://arxiv.org/abs/2409.05314}, \n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2409.05314",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 1172,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-30T02:53:29.000Z",
  "created_at": "2024-10-30T01:12:37.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67218805ebc007333b25f7e4",
  "id": "RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf",
  "modelId": "RichardErkhov/AliMaatouk_-_Gemma-2B-Tele-it-gguf",
  "sha": "54bcfcdff5054b4bdb8d6158e235f8efc28e51a7",
  "createdAt": "2024-10-30T01:12:37.000Z",
  "lastModified": "2024-10-30T02:53:29.000Z",
  "author": "RichardErkhov",
  "downloads": 1172,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}