"description":"<strong>Best overall model</strong><br><ul><li>Instruction based<li>Gives long responses<li>Curated with 300,000 uncensored instructions<li>Trained by Nous Research<li>Cannot be used commercially</ul>",
"description":"<strong>Best overall smaller model</strong><br><ul><li>Fast responses<li>Chat based<li>Trained by Mosaic ML<li>Cannot be used commercially</ul>"
},
{
"order":"c",
@ -53,16 +36,7 @@
"parameters":"7 billion",
"quant":"q4_0",
"type":"GPT-J",
"description":"
<strong>Bestoverallforcommercialusage</strong>
<br>
<ul>
<li>Fastresponses
<li>Creativeresponses</li>
<li>Instructionbased</li>
<li>TrainedbyNomicML
<li>Licensedforcommercialuse
</ul>"
"description":"<strong>Best overall for commercial usage</strong><br><ul><li>Fast responses<li>Creative responses</li><li>Instruction based</li><li>Trained by Nomic ML<li>Licensed for commercial use</ul>"
},
{
"order":"d",
@ -75,16 +49,7 @@
"parameters":"13 billion",
"quant":"q4_0",
"type":"LLaMA",
"description":"
<strong>Verygoodoverallmodel</strong>
<br>
<ul>
<li>Instructionbased
<li>BasedonthesamedatasetasGroovy
<li>SlowerthanGroovy,withhigherqualityresponses
<li>TrainedbyNomicAI
<li>Cannotbeusedcommercially
</ul>",
"description":"<strong>Very good overall model</strong><br><ul><li>Instruction based<li>Based on the same dataset as Groovy<li>Slower than Groovy, with higher quality responses<li>Trained by Nomic AI<li>Cannot be used commercially</ul>",
"description":"<strong>Good small model - trained by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego</strong><br><ul><li>Instruction based<li>Cannot be used commercially</ul>"
"description":"<strong>Good larger model - trained by teams from UC Berkeley, CMU, Stanford, MBZUAI, and UC San Diego</strong><br><ul><li>Instruction based<li>Cannot be used commercially</ul>"
"description":"<strong>Good small model - trained by by Microsoft and Peking University</strong><br><ul><li>Instruction based<li>Cannot be used commercially</ul>"
},
{
"order":"h",
@ -151,13 +98,7 @@
"parameters":"13 billion",
"quant":"q4_2",
"type":"LLaMA",
"description":"
<strong>TrainedwithRHLFbyStabilityAI</strong>
<br>
<ul>
<li>Instructionbased
<li>Cannotbeusedcommercially
</ul>"
"description":"<strong>Trained with RHLF by Stability AI</strong><br><ul><li>Instruction based<li>Cannot be used commercially</ul>"
},
{
"order":"i",
@ -170,14 +111,7 @@
"parameters":"7 billion",
"quant":"q4_0",
"type":"MPT",
"description":"
<strong>Mosaic'sinstructionmodel</strong>
<br>
<ul>
<li>Instructionbased
<li>TrainedbyMosaicML
<li>Licensedforcommercialuse
</ul>"
"description":"<strong>Mosaic's instruction model</strong><br><ul><li>Instruction based<li>Trained by Mosaic ML<li>Licensed for commercial use</ul>"
"description":"<strong>Trained for text completion with no assistant finetuning</strong><br><ul><li>Completion based<li>Trained by Mosaic ML<li>Licensed for commercial use</ul>"
},
{
"order":"k",
@ -209,14 +136,7 @@
"parameters":"13 billion",
"quant":"q4_0",
"type":"LLaMA",
"description":"
<strong>Trainedon~180,000instructions</strong>
<br>
<ul>
<li>Instructionbased
<li>TrainedbyNousResearch
<li>Cannotbeusedcommercially
</ul>"
"description":"<strong>Trained on ~180,000 instructions</strong><br><ul><li>Instruction based<li>Trained by Nous Research<li>Cannot be used commercially</ul>"
"description":"<strong>Trained on uncensored assistant data and instruction data</strong><br><ul><li>Instruction based<li>Cannot be used commercially</ul>",