GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

quantfactory/biggie-smollm-0.4b-gguf overview

This is quantized version of nisten/Biggie-SmoLlm-0.4B created using llama.cpp # Original Model Card ###Coherent Frankenstein of smolLm-0.36b upped to 0.4b This took about 5 hours of semi-automated continuous merging to figure out the recipe. Model is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit. 8bit gguf included for testing. !image/png

ggufbase_model:HuggingFaceTB/SmolLM-360M-Instructbase_model:quantized:HuggingFaceTB/SmolLM-360M-Instructendpoints_compatibleregion:usconversational
quantfactory/biggie-smollm-0.4b-gguf visual
Downloads
109
Likes
1
Pipeline
Library
Visibility
Public
Access
Open

Repository Files & Downloads

14 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Biggie-SmoLlm-0.4B.Q2_K.gguf GGUF Q2_K 228.42 MB Download
Biggie-SmoLlm-0.4B.Q3_K_L.gguf GGUF Q3_K_L 258.09 MB Download
Biggie-SmoLlm-0.4B.Q3_K_M.gguf GGUF Q3_K_M 245.53 MB Download
Biggie-SmoLlm-0.4B.Q3_K_S.gguf GGUF Q3_K_S 228.42 MB Download
Biggie-SmoLlm-0.4B.Q4_0.gguf GGUF 239.63 MB Download
Biggie-SmoLlm-0.4B.Q4_1.gguf GGUF 260.72 MB Download
Biggie-SmoLlm-0.4B.Q4_K_M.gguf GGUF Q4_K_M 284.12 MB Download
Biggie-SmoLlm-0.4B.Q4_K_S.gguf GGUF Q4_K_S 272.52 MB Download
Biggie-SmoLlm-0.4B.Q5_0.gguf GGUF 281.82 MB Download
Biggie-SmoLlm-0.4B.Q5_1.gguf GGUF 302.91 MB Download
Biggie-SmoLlm-0.4B.Q5_K_M.gguf GGUF Q5_K_M 304.89 MB Download
Biggie-SmoLlm-0.4B.Q5_K_S.gguf GGUF Q5_K_S 297.64 MB Download
Biggie-SmoLlm-0.4B.Q6_K.gguf GGUF Q6_K 387.94 MB Download
Biggie-SmoLlm-0.4B.Q8_0.gguf GGUF 408.38 MB Download

Model Details Live

Model Slug
quantfactory/biggie-smollm-0.4b-gguf
Author
QuantFactory
Pipeline Task
Library
Created
2024-08-05
Last Modified
2024-08-05
Gated
No
Private
No
HF SHA
d8c901ed6a13a57bbea72cb15616e9baa4f3980d
License
Unknown
Language
Unknown
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "HuggingFaceTB/SmolLM-360M-Instruct",
    "frontmatter": {},
    "hero_image_url": "https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ",
    "summary": "This is quantized version of nisten/Biggie-SmoLlm-0.4B created using llama.cpp # Original Model Card ###Coherent Frankenstein of smolLm-0.36b upped to 0.4b This took about 5 hours of semi-automated continuous merging to figure out the recipe. Model is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit. 8bit gguf included for testing. ``bash wget https://huggingface.co/nisten/Biggie-SmoLlm-0.4B/resolve/main/Biggie_SmolLM_400M_q8_0.gguf ` `verilog ./llama-cli -ngl 99 -co --temp 0 -p \"How to build a city on Mars via calculating Aldrin-Cycler orbits?\" -m Biggie_SmolLM_400M_q8_0.gguf -cnv -fa --keep -1 `` !image/png",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "\n---\n\nbase_model: HuggingFaceTB/SmolLM-360M-Instruct\n\n---\n\n![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)\n\n# QuantFactory/Biggie-SmoLlm-0.4B-GGUF\nThis is quantized version of [nisten/Biggie-SmoLlm-0.4B](https://huggingface.co/nisten/Biggie-SmoLlm-0.4B) created using llama.cpp\n\n# Original Model Card\n\n\n###Coherent Frankenstein of smolLm-0.36b upped to 0.4b\n\nThis took about 5 hours of semi-automated continuous merging to figure out the recipe.\nModel is smarter, and UNTRAINED. Uploaded it for training. Yet it performs well as is even quantized to 8bit.\n8bit gguf included for testing.\n\n```bash\nwget https://huggingface.co/nisten/Biggie-SmoLlm-0.4B/resolve/main/Biggie_SmolLM_400M_q8_0.gguf\n```\n```verilog\n./llama-cli -ngl 99 -co --temp 0 -p \"How to build a city on Mars via calculating Aldrin-Cycler orbits?\" -m Biggie_SmolLM_400M_q8_0.gguf -cnv -fa --keep -1\n```\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/6379683a81c1783a4a2ddba8/XgF2kz3Zz0Jqz7BEVZ96h.png)\n\n\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "base_model:HuggingFaceTB/SmolLM-360M-Instruct",
    "base_model:quantized:HuggingFaceTB/SmolLM-360M-Instruct",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 109,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-05T10:57:43.000Z",
  "created_at": "2024-08-05T10:53:49.000Z",
  "pipeline_tag": "",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "66b0af3d226848f45c75dd2e",
  "id": "QuantFactory/Biggie-SmoLlm-0.4B-GGUF",
  "modelId": "QuantFactory/Biggie-SmoLlm-0.4B-GGUF",
  "sha": "d8c901ed6a13a57bbea72cb15616e9baa4f3980d",
  "createdAt": "2024-08-05T10:53:49.000Z",
  "lastModified": "2024-08-05T10:57:43.000Z",
  "author": "QuantFactory",
  "downloads": 109,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 16
}