Model Intelligence Sheet

richarderkhov/princeton-nlp_-_llama-3-instruct-8b-dpo-gguf overview

Quantization made by Richard Erkhov. Github Discord Request more models Llama-3-Instruct-8B-DPO - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Llama-3-Instruct-8B-DPO.Q2K.gguf | Q2K | 2.96GB | | Llama-3-Instruct-8B-DPO.IQ3XS.gguf | IQ3XS | 3.28GB | | Llama-3-Instruct-8B-DPO.IQ3S.gguf | IQ3S | 3.43GB | | Llama-3-Instruct-8B-DPO.Q3KS.gguf | Q3KS | 3.41GB | | Llama-3-Instruct-8B-DPO.IQ3M.gguf | IQ3M | 3.52GB | | Llama-3-Instruct-8B-DPO.Q3K.gguf | Q3K | 3.74GB | | Llama-3-Instruct-8B-DPO.Q3KM.gguf | Q3KM | 3.74GB | | Llama-3-Instruct-8B-DPO.Q3KL.gguf | Q3KL | 4.03GB | | Llama-3-Instruct-8B-DPO.IQ4XS.gguf | IQ4XS | 4.18GB | | Llama-3-Instruct-8B-DPO.Q40.gguf | Q40 | 4.34GB | | Llama-3-Instruct-8B-DPO.IQ4NL.gguf | IQ4NL | 4.38GB | | Llama-3-Instruct-8B-DPO.Q4KS.gguf | Q4KS | 4.37GB | | Llama-3-Instruct-8B-DPO.Q4K.gguf | Q4K | 4.58GB | | Llama-3-Instruct-8B-DPO.Q4KM.gguf | Q4KM | 4.58GB | | Llama-3-Instruct-8B-DPO.Q41.gguf | Q41 | 4.78GB | | Llama-3-Instruct-8B-DPO.Q50.gguf | Q50 | 5.21GB | | Llama-3-Instruct-8B-DPO.Q5KS.gguf | Q5KS | 5.21GB | | Llama-3-Instruct-8B-DPO.Q5K.gguf | Q5K | 5.34GB | | Llama-3-Instruct-8B-DPO.Q5KM.gguf | Q5KM | 5.34GB | | Llama-3-Instruct-8B-DPO.Q51.gguf | Q51 | 5.65GB | | Llama-3-Instruct-8B-DPO.Q6K.gguf | Q6K | 6.14GB | | Llama-3-Instruct-8B-DPO.Q80.gguf | Q80 | 7.95GB | Original model description: This is a model released from the preprint: SimPO: Simple Preference Optimization with a Reference-Free Reward Please refer to our repository for more details.

ggufarxiv:2405.14734endpoints_compatibleregion:usconversational

richarderkhov/princeton-nlp_-_llama-3-instruct-8b-dpo-gguf visual

Downloads

171

Likes

Pipeline

—

Library

—

Visibility

Public

Access

Open

Repository Files & Downloads

22 files detected

Direct downloads for all repository files

File	Type	Quantization	Size	Link
Llama-3-Instruct-8B-DPO.IQ3_M.gguf	GGUF	IQ3_M	3.52 GB	Download
Llama-3-Instruct-8B-DPO.IQ3_S.gguf	GGUF	IQ3_S	3.43 GB	Download
Llama-3-Instruct-8B-DPO.IQ3_XS.gguf	GGUF	IQ3_XS	3.28 GB	Download
Llama-3-Instruct-8B-DPO.IQ4_NL.gguf	GGUF	IQ4_NL	4.38 GB	Download
Llama-3-Instruct-8B-DPO.IQ4_XS.gguf	GGUF	IQ4_XS	4.18 GB	Download
Llama-3-Instruct-8B-DPO.Q2_K.gguf	GGUF	Q2_K	2.96 GB	Download
Llama-3-Instruct-8B-DPO.Q3_K.gguf	GGUF	Q3_K	3.74 GB	Download
Llama-3-Instruct-8B-DPO.Q3_K_L.gguf	GGUF	Q3_K_L	4.03 GB	Download
Llama-3-Instruct-8B-DPO.Q3_K_M.gguf	GGUF	Q3_K_M	3.74 GB	Download
Llama-3-Instruct-8B-DPO.Q3_K_S.gguf	GGUF	Q3_K_S	3.41 GB	Download
Llama-3-Instruct-8B-DPO.Q4_0.gguf	GGUF	—	4.34 GB	Download
Llama-3-Instruct-8B-DPO.Q4_1.gguf	GGUF	—	4.78 GB	Download
Llama-3-Instruct-8B-DPO.Q4_K.gguf	GGUF	Q4_K	4.58 GB	Download
Llama-3-Instruct-8B-DPO.Q4_K_M.gguf	GGUF	Q4_K_M	4.58 GB	Download
Llama-3-Instruct-8B-DPO.Q4_K_S.gguf	GGUF	Q4_K_S	4.37 GB	Download
Llama-3-Instruct-8B-DPO.Q5_0.gguf	GGUF	—	5.21 GB	Download
Llama-3-Instruct-8B-DPO.Q5_1.gguf	GGUF	—	5.65 GB	Download
Llama-3-Instruct-8B-DPO.Q5_K.gguf	GGUF	Q5_K	5.34 GB	Download
Llama-3-Instruct-8B-DPO.Q5_K_M.gguf	GGUF	Q5_K_M	5.34 GB	Download
Llama-3-Instruct-8B-DPO.Q5_K_S.gguf	GGUF	Q5_K_S	5.21 GB	Download
Llama-3-Instruct-8B-DPO.Q6_K.gguf	GGUF	Q6_K	6.14 GB	Download
Llama-3-Instruct-8B-DPO.Q8_0.gguf	GGUF	—	7.95 GB	Download

Model Details Live

Model Slug

richarderkhov/princeton-nlp_-_llama-3-instruct-8b-dpo-gguf

Author

RichardErkhov

Pipeline Task

—

Library

—

Created

2024-10-04

Last Modified

2024-10-04

Gated

Private

HF SHA

58c0d4d54541098270e1db988bb34fe7eacc7686

License

Unknown

Language

Unknown

Base Model

Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Llama-3-Instruct-8B-DPO - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Llama-3-Instruct-8B-DPO.Q2_K.gguf | Q2_K | 2.96GB | | Llama-3-Instruct-8B-DPO.IQ3_XS.gguf | IQ3_XS | 3.28GB | | Llama-3-Instruct-8B-DPO.IQ3_S.gguf | IQ3_S | 3.43GB | | Llama-3-Instruct-8B-DPO.Q3_K_S.gguf | Q3_K_S | 3.41GB | | Llama-3-Instruct-8B-DPO.IQ3_M.gguf | IQ3_M | 3.52GB | | Llama-3-Instruct-8B-DPO.Q3_K.gguf | Q3_K | 3.74GB | | Llama-3-Instruct-8B-DPO.Q3_K_M.gguf | Q3_K_M | 3.74GB | | Llama-3-Instruct-8B-DPO.Q3_K_L.gguf | Q3_K_L | 4.03GB | | Llama-3-Instruct-8B-DPO.IQ4_XS.gguf | IQ4_XS | 4.18GB | | Llama-3-Instruct-8B-DPO.Q4_0.gguf | Q4_0 | 4.34GB | | Llama-3-Instruct-8B-DPO.IQ4_NL.gguf | IQ4_NL | 4.38GB | | Llama-3-Instruct-8B-DPO.Q4_K_S.gguf | Q4_K_S | 4.37GB | | Llama-3-Instruct-8B-DPO.Q4_K.gguf | Q4_K | 4.58GB | | Llama-3-Instruct-8B-DPO.Q4_K_M.gguf | Q4_K_M | 4.58GB | | Llama-3-Instruct-8B-DPO.Q4_1.gguf | Q4_1 | 4.78GB | | Llama-3-Instruct-8B-DPO.Q5_0.gguf | Q5_0 | 5.21GB | | Llama-3-Instruct-8B-DPO.Q5_K_S.gguf | Q5_K_S | 5.21GB | | Llama-3-Instruct-8B-DPO.Q5_K.gguf | Q5_K | 5.34GB | | Llama-3-Instruct-8B-DPO.Q5_K_M.gguf | Q5_K_M | 5.34GB | | Llama-3-Instruct-8B-DPO.Q5_1.gguf | Q5_1 | 5.65GB | | Llama-3-Instruct-8B-DPO.Q6_K.gguf | Q6_K | 6.14GB | | Llama-3-Instruct-8B-DPO.Q8_0.gguf | Q8_0 | 7.95GB | Original model description: This is a model released from the preprint: *SimPO: Simple Preference Optimization with a Reference-Free Reward*  Please refer to our repository for more details.",
    "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\nLlama-3-Instruct-8B-DPO - GGUF\n- Model creator: https://huggingface.co/princeton-nlp/\n- Original model: https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-DPO/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3-Instruct-8B-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q2_K.gguf) | Q2_K | 2.96GB |\n| [Llama-3-Instruct-8B-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [Llama-3-Instruct-8B-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [Llama-3-Instruct-8B-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [Llama-3-Instruct-8B-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [Llama-3-Instruct-8B-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q3_K.gguf) | Q3_K | 3.74GB |\n| [Llama-3-Instruct-8B-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [Llama-3-Instruct-8B-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [Llama-3-Instruct-8B-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [Llama-3-Instruct-8B-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [Llama-3-Instruct-8B-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [Llama-3-Instruct-8B-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [Llama-3-Instruct-8B-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q4_K.gguf) | Q4_K | 4.58GB |\n| [Llama-3-Instruct-8B-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [Llama-3-Instruct-8B-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [Llama-3-Instruct-8B-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [Llama-3-Instruct-8B-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [Llama-3-Instruct-8B-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q5_K.gguf) | Q5_K | 5.34GB |\n| [Llama-3-Instruct-8B-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [Llama-3-Instruct-8B-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [Llama-3-Instruct-8B-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q6_K.gguf) | Q6_K | 6.14GB |\n| [Llama-3-Instruct-8B-DPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf/blob/main/Llama-3-Instruct-8B-DPO.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\nThis is a model released from the preprint: *[SimPO: Simple Preference Optimization with a Reference-Free Reward](https://arxiv.org/abs/2405.14734)*  Please refer to our [repository](https://github.com/princeton-nlp/SimPO) for more details.\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2405.14734",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 171,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-04T21:26:52.000Z",
  "created_at": "2024-10-04T15:07:00.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

Source payload excerpt (from Hugging Face API)

{
  "_id": "670004945534a5d90b7fb198",
  "id": "RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf",
  "modelId": "RichardErkhov/princeton-nlp_-_Llama-3-Instruct-8B-DPO-gguf",
  "sha": "58c0d4d54541098270e1db988bb34fe7eacc7686",
  "createdAt": "2024-10-04T15:07:00.000Z",
  "lastModified": "2024-10-04T21:26:52.000Z",
  "author": "RichardErkhov",
  "downloads": 171,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}