richarderkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown 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\nllama8b-gsm-real-sftsd1 - GGUF\n- Model creator: https://huggingface.co/jkazdan/\n- Original model: https://huggingface.co/jkazdan/llama8b-gsm-real-sftsd1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [llama8b-gsm-real-sftsd1.Q2_K.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q2_K.gguf) | Q2_K | 2.96GB |\n| [llama8b-gsm-real-sftsd1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.IQ3_XS.gguf) | IQ3_XS | 3.28GB |\n| [llama8b-gsm-real-sftsd1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.IQ3_S.gguf) | IQ3_S | 3.43GB |\n| [llama8b-gsm-real-sftsd1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q3_K_S.gguf) | Q3_K_S | 3.41GB |\n| [llama8b-gsm-real-sftsd1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.IQ3_M.gguf) | IQ3_M | 3.52GB |\n| [llama8b-gsm-real-sftsd1.Q3_K.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q3_K.gguf) | Q3_K | 3.74GB |\n| [llama8b-gsm-real-sftsd1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q3_K_M.gguf) | Q3_K_M | 3.74GB |\n| [llama8b-gsm-real-sftsd1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q3_K_L.gguf) | Q3_K_L | 4.03GB |\n| [llama8b-gsm-real-sftsd1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.IQ4_XS.gguf) | IQ4_XS | 4.18GB |\n| [llama8b-gsm-real-sftsd1.Q4_0.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q4_0.gguf) | Q4_0 | 4.34GB |\n| [llama8b-gsm-real-sftsd1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.IQ4_NL.gguf) | IQ4_NL | 4.38GB |\n| [llama8b-gsm-real-sftsd1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q4_K_S.gguf) | Q4_K_S | 4.37GB |\n| [llama8b-gsm-real-sftsd1.Q4_K.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q4_K.gguf) | Q4_K | 4.58GB |\n| [llama8b-gsm-real-sftsd1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q4_K_M.gguf) | Q4_K_M | 4.58GB |\n| [llama8b-gsm-real-sftsd1.Q4_1.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q4_1.gguf) | Q4_1 | 4.78GB |\n| [llama8b-gsm-real-sftsd1.Q5_0.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q5_0.gguf) | Q5_0 | 5.21GB |\n| [llama8b-gsm-real-sftsd1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q5_K_S.gguf) | Q5_K_S | 5.21GB |\n| [llama8b-gsm-real-sftsd1.Q5_K.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q5_K.gguf) | Q5_K | 5.34GB |\n| [llama8b-gsm-real-sftsd1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q5_K_M.gguf) | Q5_K_M | 5.34GB |\n| [llama8b-gsm-real-sftsd1.Q5_1.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q5_1.gguf) | Q5_1 | 5.65GB |\n| [llama8b-gsm-real-sftsd1.Q6_K.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.Q6_K.gguf) | Q6_K | 6.14GB |\n| [llama8b-gsm-real-sftsd1.Q8_0.gguf](https://huggingface.co/RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf/blob/main/llama8b-gsm-real-sftsd1.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-Instruct\ntags:\n- trl\n- sft\n- generated_from_trainer\nmodel-index:\n- name: llama8b-gsm-real-sftsd1\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# llama8b-gsm-real-sftsd1\n\nThis model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 1.0750\n- Num Input Tokens Seen: 1235796\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: 8e-06\n- train_batch_size: 2\n- eval_batch_size: 2\n- seed: 1\n- gradient_accumulation_steps: 16\n- total_train_batch_size: 32\n- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments\n- lr_scheduler_type: constant_with_warmup\n- lr_scheduler_warmup_ratio: 0.05\n- num_epochs: 1\n\n### Training results\n\n| Training Loss | Epoch  | Step | Validation Loss | Input Tokens Seen |\n|:-------------:|:------:|:----:|:---------------:|:-----------------:|\n| No log        | 0      | 0    | 1.8595          | 0                 |\n| 1.7608        | 0.0214 | 5    | 1.6700          | 25930             |\n| 1.3248        | 0.0428 | 10   | 1.3475          | 52270             |\n| 1.2071        | 0.0642 | 15   | 1.2084          | 79554             |\n| 1.1995        | 0.0856 | 20   | 1.1763          | 105102            |\n| 1.0962        | 0.1070 | 25   | 1.1607          | 131956            |\n| 1.1212        | 0.1284 | 30   | 1.1494          | 158684            |\n| 1.1985        | 0.1499 | 35   | 1.1423          | 184480            |\n| 1.0998        | 0.1713 | 40   | 1.1370          | 211054            |\n| 1.1959        | 0.1927 | 45   | 1.1324          | 236974            |\n| 1.1464        | 0.2141 | 50   | 1.1279          | 262912            |\n| 1.2088        | 0.2355 | 55   | 1.1243          | 289396            |\n| 1.0862        | 0.2569 | 60   | 1.1215          | 316814            |\n| 1.17          | 0.2783 | 65   | 1.1191          | 342274            |\n| 1.079         | 0.2997 | 70   | 1.1173          | 369198            |\n| 1.155         | 0.3211 | 75   | 1.1141          | 396132            |\n| 1.122         | 0.3425 | 80   | 1.1118          | 421548            |\n| 1.0646        | 0.3639 | 85   | 1.1104          | 449306            |\n| 1.1247        | 0.3853 | 90   | 1.1071          | 473942            |\n| 1.0455        | 0.4067 | 95   | 1.1065          | 500546            |\n| 1.1771        | 0.4282 | 100  | 1.1047          | 525364            |\n| 1.0121        | 0.4496 | 105  | 1.1031          | 552868            |\n| 1.0939        | 0.4710 | 110  | 1.1028          | 579098            |\n| 1.133         | 0.4924 | 115  | 1.1005          | 604876            |\n| 1.0363        | 0.5138 | 120  | 1.0987          | 629760            |\n| 0.9986        | 0.5352 | 125  | 1.0972          | 657158            |\n| 1.0632        | 0.5566 | 130  | 1.0968          | 683064            |\n| 1.0441        | 0.5780 | 135  | 1.0940          | 710802            |\n| 1.0112        | 0.5994 | 140  | 1.0930          | 737182            |\n| 1.0467        | 0.6208 | 145  | 1.0914          | 763298            |\n| 1.0917        | 0.6422 | 150  | 1.0897          | 790790            |\n| 1.0613        | 0.6636 | 155  | 1.0891          | 818288            |\n| 0.9827        | 0.6850 | 160  | 1.0883          | 845282            |\n| 1.1266        | 0.7064 | 165  | 1.0874          | 870452            |\n| 1.0661        | 0.7279 | 170  | 1.0859          | 896976            |\n| 1.1039        | 0.7493 | 175  | 1.0852          | 923846            |\n| 1.0813        | 0.7707 | 180  | 1.0842          | 949236            |\n| 1.0729        | 0.7921 | 185  | 1.0835          | 977230            |\n| 1.0617        | 0.8135 | 190  | 1.0838          | 1003880           |\n| 1.1071        | 0.8349 | 195  | 1.0825          | 1029762           |\n| 1.0408        | 0.8563 | 200  | 1.0810          | 1057616           |\n| 1.0801        | 0.8777 | 205  | 1.0799          | 1084200           |\n| 1.0656        | 0.8991 | 210  | 1.0786          | 1110340           |\n| 1.1181        | 0.9205 | 215  | 1.0787          | 1136600           |\n| 0.9485        | 0.9419 | 220  | 1.0782          | 1164358           |\n| 1.0608        | 0.9633 | 225  | 1.0772          | 1192626           |\n| 1.1137        | 0.9847 | 230  | 1.0755          | 1219714           |\n\n\n### Framework versions\n\n- Transformers 4.46.0\n- Pytorch 2.4.1.post300\n- Datasets 2.20.0\n- Tokenizers 0.20.1\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 95,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-07T14:33:56.000Z",
  "created_at": "2025-07-07T13:34:39.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "686bcceffb1d29bf991ccffe",
  "id": "RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf",
  "modelId": "RichardErkhov/jkazdan_-_llama8b-gsm-real-sftsd1-gguf",
  "sha": "ea00d844c421c438a8965e4f41d3181d247808e2",
  "createdAt": "2025-07-07T13:34:39.000Z",
  "lastModified": "2025-07-07T14:33:56.000Z",
  "author": "RichardErkhov",
  "downloads": 95,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}