richarderkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on the llama-duo/synth_coding_dataset_dedup dataset. It achieves the following results on the evaluation set:",
    "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\nllama3.1-8b-gpt4o_100k_coding-fft - GGUF\n- Model creator: https://huggingface.co/klcsp/\n- Original model: https://huggingface.co/klcsp/llama3.1-8b-gpt4o_100k_coding-fft/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q2_K.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.IQ3_S.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.IQ3_M.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q3_K.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q4_0.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q4_K.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q4_1.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q5_0.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q5_K.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q5_1.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q6_K.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama3.1-8b-gpt4o_100k_coding-fft.Q8_0.gguf](https://huggingface.co/RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf/blob/main/llama3.1-8b-gpt4o_100k_coding-fft.Q8_0.gguf) | Q8_0 | 7.95GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: llama3\nbase_model: meta-llama/Meta-Llama-3-8B\ntags:\n- alignment-handbook\n- trl\n- sft\n- generated_from_trainer\n- trl\n- sft\n- generated_from_trainer\ndatasets:\n- llama-duo/synth_coding_dataset_dedup\nmodel-index:\n- name: llama3.1-8b-gpt4o_100k_coding-fft\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n# llama3.1-8b-gpt4o_100k_coding-fft\n\nThis model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the llama-duo/synth_coding_dataset_dedup dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 2.2535\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0003\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 32\n- total_eval_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss |\n|:-------------:|:------:|:----:|:---------------:|\n| 0.5499        | 0.9991 | 539  | 2.2535          |\n\n\n### Framework versions\n\n- Transformers 4.45.1\n- Pytorch 2.4.1+cu121\n- Datasets 3.0.1\n- Tokenizers 0.20.0\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 156,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-12T05:09:33.000Z",
  "created_at": "2025-07-12T04:04:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6871deb46236a362e81b8607",
  "id": "RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf",
  "modelId": "RichardErkhov/klcsp_-_llama3.1-8b-gpt4o_100k_coding-fft-gguf",
  "sha": "0e42ef16df1da7544e03ba5bdd19acb1add9c748",
  "createdAt": "2025-07-12T04:04:04.000Z",
  "lastModified": "2025-07-12T05:09:33.000Z",
  "author": "RichardErkhov",
  "downloads": 156,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}