GraySoft
Projects Models About FAQ Contact Download guIDE →

epistemeai/dolphin-llama-3.1-8b-orpo-v0.1-4bit-gguf Q4_K_M GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

epistemeai/dolphin-llama-3.1-8b-orpo-v0.1-4bit-gguf overview

gguf: This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license. Fine-tune using ORPO

transformersggufllamatext-generation-inferenceunslothtrlsftdpotext-generationendataset:reciperesearch/dolphin-sft-v0.1-preferencebase_model:unsloth/Meta-Llama-3.1-8B-bnb-4bitbase_model:quantized:unsloth/Meta-Llama-3.1-8B-bnb-4bitlicense:llama3.1endpoints_compatibleregion:usconversational
epistemeai/dolphin-llama-3.1-8b-orpo-v0.1-4bit-gguf visual
Downloads
171
Likes
2
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

2 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
unsloth.F16.gguf GGUF F16 14.97 GB Download
unsloth.Q4_K_M.gguf GGUF Q4_K_M 4.58 GB Download

Model Details Live

Model Slug
epistemeai/dolphin-llama-3.1-8b-orpo-v0.1-4bit-gguf
Author
EpistemeAI
Pipeline Task
text-generation
Library
transformers
Created
2024-08-09
Last Modified
2024-08-09
Gated
No
Private
No
HF SHA
4c0c6b33fd045d8aac43bde17dec15fddb456340
License
llama3.1
Language
en
Base Model
unsloth/Meta-Llama-3.1-8B-bnb-4bit

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
    "language": [
      "en"
    ],
    "tags": [
      "text-generation-inference",
      "transformers",
      "unsloth",
      "llama",
      "trl",
      "sft",
      "dpo"
    ],
    "license": "llama3.1",
    "datasets": [
      "reciperesearch/dolphin-sft-v0.1-preference"
    ],
    "pipeline_tag": "text-generation",
    "license_name": "llama3",
    "license_link": "LICENSE",
    "model_creator": "EpistemeAI",
    "quantized_by": "EpistemeAI",
    "frontmatter": {
      "base_model": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
      "language": [
        "en"
      ],
      "tags": [
        "text-generation-inference",
        "transformers",
        "unsloth",
        "llama",
        "trl",
        "sft",
        "dpo"
      ],
      "license": "llama3.1",
      "datasets": [
        "reciperesearch/dolphin-sft-v0.1-preference"
      ],
      "pipeline_tag": "text-generation",
      "license_name": "llama3",
      "license_link": "LICENSE",
      "model_creator": "EpistemeAI",
      "quantized_by": "EpistemeAI"
    },
    "hero_image_url": "",
    "summary": "**gguf**: This model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license. Fine-tune using ORPO",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit\nlanguage:\n- en\ntags:\n- text-generation-inference\n- transformers\n- unsloth\n- llama\n- trl\n- sft\n- dpo\nlicense: llama3.1\ndatasets:\n- reciperesearch/dolphin-sft-v0.1-preference\npipeline_tag: text-generation\nlicense_name: llama3\nlicense_link: LICENSE\nmodel_creator: EpistemeAI\nquantized_by: EpistemeAI\n---\n\n**gguf**:\n- q4_k_m\n- 16-bit\n\n\nThis model is based on Meta Llama 3.1 8b, and is governed by the Llama 3.1 license.\n\nFine-tune using ORPO\n\n## Training Details\n\n### Training Data\n\n- dataset: reciperesearch/dolphin-sft-v0.1-preference\n\n### Training Procedure\nORPO techniques\n\n\n#### Training Hyperparameters\n\n- **Training regime:** {{ training_regime | default(\"[More Information Needed]\", true)}} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->\n\n\n\nTrainOutput(global_step=30, training_loss=4.25380277633667, metrics={'train_runtime': 679.3467, 'train_samples_per_second': 0.353, 'train_steps_per_second': 0.044, 'total_flos': 0.0, 'train_loss': 4.25380277633667, 'epoch': 0.015})",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "llama",
    "text-generation-inference",
    "unsloth",
    "trl",
    "sft",
    "dpo",
    "text-generation",
    "en",
    "dataset:reciperesearch/dolphin-sft-v0.1-preference",
    "base_model:unsloth/Meta-Llama-3.1-8B-bnb-4bit",
    "base_model:quantized:unsloth/Meta-Llama-3.1-8B-bnb-4bit",
    "license:llama3.1",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 171,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-09T23:07:12.000Z",
  "created_at": "2024-08-09T20:15:11.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "66b678cfc8ae5d732849fdf7",
  "id": "EpistemeAI/Dolphin-Llama-3.1-8B-orpo-v0.1-4bit-gguf",
  "modelId": "EpistemeAI/Dolphin-Llama-3.1-8B-orpo-v0.1-4bit-gguf",
  "sha": "4c0c6b33fd045d8aac43bde17dec15fddb456340",
  "createdAt": "2024-08-09T20:15:11.000Z",
  "lastModified": "2024-08-09T23:07:12.000Z",
  "author": "EpistemeAI",
  "downloads": 171,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 5
}