afrideva/smol_llama-220m-gqa-gguf Q6_K 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
afrideva/smol_llama-220m-gqa-gguf overview
model card WIP, more details to come A small 220M param (total) decoder model. This is the first version of the model. ---
Downloads
115
Likes
0
Pipeline
text-generation
Library
—
Visibility
Public
Access
Open
Repository Files & Downloads
7 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| smol_llama-220m-gqa.fp16.gguf | GGUF | — | 416.28 MB | Download |
| smol_llama-220m-gqa.q2_k.gguf | GGUF | Q2_K | 97.85 MB | Download |
| smol_llama-220m-gqa.q3_k_m.gguf | GGUF | Q3_K_M | 110.34 MB | Download |
| smol_llama-220m-gqa.q4_k_m.gguf | GGUF | Q4_K_M | 131.21 MB | Download |
| smol_llama-220m-gqa.q5_k_m.gguf | GGUF | Q5_K_M | 150.60 MB | Download |
| smol_llama-220m-gqa.q6_k.gguf | GGUF | Q6_K | 171.20 MB | Download |
| smol_llama-220m-gqa.q8_0.gguf | GGUF | — | 221.52 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"base_model": "BEE-spoke-data/smol_llama-220M-GQA",
"datasets": [
"JeanKaddour/minipile",
"pszemraj/simple_wikipedia_LM",
"mattymchen/refinedweb-3m",
"BEE-spoke-data/knowledge-inoc-concat-v1"
],
"inference": false,
"language": [
"en"
],
"license": "apache-2.0",
"model_creator": "BEE-spoke-data",
"model_name": "smol_llama-220M-GQA",
"pipeline_tag": "text-generation",
"quantized_by": "afrideva",
"tags": [
"smol_llama",
"llama2",
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0"
],
"widget": [
{
"example_title": "El Microondas",
"text": "My name is El Microondas the Wise, and"
},
{
"example_title": "Kennesaw State University",
"text": "Kennesaw State University is a public"
},
{
"example_title": "Bungie",
"text": "Bungie Studios is an American video game developer. They are most famous for developing the award winning Halo series of video games. They also made Destiny. The studio was founded"
},
{
"example_title": "Mona Lisa",
"text": "The Mona Lisa is a world-renowned painting created by"
},
{
"example_title": "Harry Potter Series",
"text": "The Harry Potter series, written by J.K. Rowling, begins with the book titled"
},
{
"example_title": "Riddle",
"text": "Question: I have cities, but no houses. I have mountains, but no trees. I have water, but no fish. What am I?\nAnswer:"
},
{
"example_title": "Photosynthesis",
"text": "The process of photosynthesis involves the conversion of"
},
{
"example_title": "Story Continuation",
"text": "Jane went to the store to buy some groceries. She picked up apples, oranges, and a loaf of bread. When she got home, she realized she forgot"
},
{
"example_title": "Math Problem",
"text": "Problem 2: If a train leaves Station A at 9:00 AM and travels at 60 mph, and another train leaves Station B at 10:00 AM and travels at 80 mph, when will they meet if the distance between the stations is 300 miles?\nTo determine"
},
{
"example_title": "Algorithm Definition",
"text": "In the context of computer programming, an algorithm is"
}
],
"frontmatter": {
"base_model": "BEE-spoke-data/smol_llama-220M-GQA",
"datasets": [
"JeanKaddour/minipile",
"pszemraj/simple_wikipedia_LM",
"mattymchen/refinedweb-3m",
"BEE-spoke-data/knowledge-inoc-concat-v1"
],
"inference": "false",
"language": [
"en"
],
"license": "apache-2.0",
"model_creator": "BEE-spoke-data",
"model_name": "smol_llama-220M-GQA",
"pipeline_tag": "text-generation",
"quantized_by": "afrideva",
"tags": [
"smol_llama",
"llama2",
"gguf",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0"
],
"widget": [
"example_title: El Microondas",
"example_title: Kennesaw State University",
"example_title: Bungie",
"example_title: Mona Lisa",
"example_title: Harry Potter Series",
"example_title: Riddle",
"example_title: Photosynthesis",
"example_title: Story Continuation",
"example_title: Math Problem",
"example_title: Algorithm Definition"
]
},
"hero_image_url": "",
"summary": "> model card WIP, more details to come A small 220M param (total) decoder model. This is the first version of the model. ---",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nbase_model: BEE-spoke-data/smol_llama-220M-GQA\ndatasets:\n- JeanKaddour/minipile\n- pszemraj/simple_wikipedia_LM\n- mattymchen/refinedweb-3m\n- BEE-spoke-data/knowledge-inoc-concat-v1\ninference: false\nlanguage:\n- en\nlicense: apache-2.0\nmodel_creator: BEE-spoke-data\nmodel_name: smol_llama-220M-GQA\npipeline_tag: text-generation\nquantized_by: afrideva\ntags:\n- smol_llama\n- llama2\n- gguf\n- ggml\n- quantized\n- q2_k\n- q3_k_m\n- q4_k_m\n- q5_k_m\n- q6_k\n- q8_0\nwidget:\n- example_title: El Microondas\n text: My name is El Microondas the Wise, and\n- example_title: Kennesaw State University\n text: Kennesaw State University is a public\n- example_title: Bungie\n text: Bungie Studios is an American video game developer. They are most famous for\n developing the award winning Halo series of video games. They also made Destiny.\n The studio was founded\n- example_title: Mona Lisa\n text: The Mona Lisa is a world-renowned painting created by\n- example_title: Harry Potter Series\n text: The Harry Potter series, written by J.K. Rowling, begins with the book titled\n- example_title: Riddle\n text: 'Question: I have cities, but no houses. I have mountains, but no trees. I\n have water, but no fish. What am I?\n\n Answer:'\n- example_title: Photosynthesis\n text: The process of photosynthesis involves the conversion of\n- example_title: Story Continuation\n text: Jane went to the store to buy some groceries. She picked up apples, oranges,\n and a loaf of bread. When she got home, she realized she forgot\n- example_title: Math Problem\n text: 'Problem 2: If a train leaves Station A at 9:00 AM and travels at 60 mph,\n and another train leaves Station B at 10:00 AM and travels at 80 mph, when will\n they meet if the distance between the stations is 300 miles?\n\n To determine'\n- example_title: Algorithm Definition\n text: In the context of computer programming, an algorithm is\n---\n# BEE-spoke-data/smol_llama-220M-GQA-GGUF\n\nQuantized GGUF model files for [smol_llama-220M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA) from [BEE-spoke-data](https://huggingface.co/BEE-spoke-data)\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [smol_llama-220m-gqa.fp16.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.fp16.gguf) | fp16 | 436.50 MB |\n| [smol_llama-220m-gqa.q2_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q2_k.gguf) | q2_k | 102.60 MB |\n| [smol_llama-220m-gqa.q3_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q3_k_m.gguf) | q3_k_m | 115.70 MB |\n| [smol_llama-220m-gqa.q4_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q4_k_m.gguf) | q4_k_m | 137.58 MB |\n| [smol_llama-220m-gqa.q5_k_m.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q5_k_m.gguf) | q5_k_m | 157.91 MB |\n| [smol_llama-220m-gqa.q6_k.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q6_k.gguf) | q6_k | 179.52 MB |\n| [smol_llama-220m-gqa.q8_0.gguf](https://huggingface.co/afrideva/smol_llama-220M-GQA-GGUF/resolve/main/smol_llama-220m-gqa.q8_0.gguf) | q8_0 | 232.28 MB |\n\n\n\n## Original Model Card:\n# smol_llama: 220M GQA\n\n> model card WIP, more details to come\n\n\nA small 220M param (total) decoder model. This is the first version of the model.\n\n- 1024 hidden size, 10 layers\n- GQA (32 heads, 8 key-value), context length 2048\n- train-from-scratch on one GPU :)\n\n\n---",
"related_quantizations": []
},
"tags": [
"gguf",
"smol_llama",
"llama2",
"ggml",
"quantized",
"q2_k",
"q3_k_m",
"q4_k_m",
"q5_k_m",
"q6_k",
"q8_0",
"text-generation",
"en",
"dataset:JeanKaddour/minipile",
"dataset:pszemraj/simple_wikipedia_LM",
"dataset:mattymchen/refinedweb-3m",
"dataset:BEE-spoke-data/knowledge-inoc-concat-v1",
"base_model:BEE-spoke-data/smol_llama-220M-GQA",
"base_model:quantized:BEE-spoke-data/smol_llama-220M-GQA",
"license:apache-2.0",
"region:us"
],
"likes": 0,
"downloads": 115,
"gated": false,
"private": false,
"last_modified": "2023-12-27T16:31:06.000Z",
"created_at": "2023-12-27T16:30:10.000Z",
"pipeline_tag": "text-generation",
"library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
"_id": "658c51125a8f8a309e8dccb7",
"id": "afrideva/smol_llama-220M-GQA-GGUF",
"modelId": "afrideva/smol_llama-220M-GQA-GGUF",
"sha": "4d4d4af3f486eee889cab3b48326e7ab319f2953",
"createdAt": "2023-12-27T16:30:10.000Z",
"lastModified": "2023-12-27T16:31:06.000Z",
"author": "afrideva",
"downloads": 115,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "text-generation",
"library_name": "",
"siblings_count": 9
}