Upload models.json

models.json

@@ -13,7 +13,7 @@
         "model_description": "It is an AI assistant who can talk with you and help solve simple problems. It's based on a lite LLAMA2 model developed by Meta Inc.",
         "developer": "Meta",
         "developer_url": "https://ai.meta.com/llama/",
-        "category": "Talk & Inference"
+        "category": "Talk & Inference",
         "file_size": 1430,
         "context" : 2048,
         "max_context" : 2048,
@@ -49,7 +49,7 @@
          "model_description": "It's a very small LLAMA2 model with only 460M parameters trained with 1T tokens. It's best for testing.",
          "developer": "Xiaotian Han from Texas A&M University",
          "developer_url": "https://huggingface.co/ahxt/LiteLlama-460M-1T",
-         "category": "Test"
+         "category": "Test",
          "file_size": 493,
          "context" : 1024,
          "max_context" : 1024,
@@ -85,7 +85,7 @@
          "model_description": "The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of just 90 days using 16 A100-40G GPUs. The training has started on 2023-09-01.",
          "developer": "Zhang Peiyuan",
          "developer_url": "https://github.com/jzhang38/TinyLlama",
-         "category": "Talk & Inference"
+         "category": "Talk & Inference",
          "file_size": 1170,
          "context" : 4096,
          "max_context" : 4096,
@@ -121,7 +121,7 @@
         "model_description": "The Mistral-7B-v0.2 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.2 outperforms Llama 2 13B on all benchmarks we tested.",
         "developer": "Mistral AI",
         "developer_url": "https://mistral.ai/",
-        "category": "Best Q&A for latest devices"
+        "category": "Best Q&A for latest devices",
         "file_size": 7695,
         "context" : 4096,
         "max_context" : 4096,
@@ -157,7 +157,7 @@
         "model_description": "OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning. Our models learn from mixed-quality data without preference labels, delivering exceptional performance on par with ChatGPT, even with a 7B model. Despite our simple approach, we are committed to developing a high-performance, commercially viable, open-source large language model, and we continue to make significant strides toward this vision.",
         "developer": "OpenChat Team",
         "developer_url": "https://openchat.team/",
-        "category": "Best Q&A for latest devices"
+        "category": "Best Q&A for latest devices",
         "file_size": 7695,
         "context" : 4096,
         "max_context" : 4096,
@@ -193,7 +193,7 @@
         "model_description": "Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (for safety and educational value). When assessed against benchmarks testing common sense, language understanding, and logical reasoning, Phi-2 showcased a nearly state-of-the-art performance among models with less than 13 billion parameters.",
         "developer": "Microsoft",
         "developer_url": "https://huggingface.co/microsoft/phi-2",
-        "category": "Math Q&A"
+        "category": "Math Q&A",
         "file_size": 2960,
         "context" : 4096,
         "max_context" : 4096,
@@ -265,7 +265,7 @@
         "model_description": "Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models. Developed by Google DeepMind and other teams across Google, Gemma is named after the Latin gemma, meaning 'precious stone.' The Gemma model weights are supported by developer tools that promote innovation, collaboration, and the responsible use of artificial intelligence (AI).",
         "developer": "Google",
         "developer_url": "https://huggingface.co/google",
-        "category": "Talk & Inference"
+        "category": "Talk & Inference",
         "file_size": 2669,
         "context" : 8192,
         "max_context" : 8192,
@@ -301,7 +301,7 @@
         "model_description": "StarCoder2-3B model is a 3B parameter model trained on 17 programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 3+ trillion tokens",
         "developer": "Bigcode",
         "developer_url": "https://www.bigcode-project.org/",
-        "category": "Programming Assistance"
+        "category": "Programming Assistance",
         "file_size": 3220,
         "context" : 8192,
         "max_context" : 8192,
@@ -373,7 +373,7 @@
         "model_description": "This model is based on Mistral-7b-v0.2 with 16k context lengths. It's a uncensored model and supports a variety of instruction, conversational, and coding skills.",
         "developer": "Eric Hartford and Cognitive Computations",
         "developer_url": "https://erichartford.com/",
-        "category": "Best Q&A for latest devices"
+        "category": "Best Q&A for latest devices",
         "file_size": 2728,
         "context" : 16384,
         "max_context" : 16384,
@@ -409,7 +409,7 @@
         "model_description": "The WizardLM-2 is one of the next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent.",
         "developer": "Eric Hartford and Cognitive Computations",
         "developer_url": "https://huggingface.co/collections/microsoft/wizardlm-661d403f71e6c8257dbd598a",
-        "category": "Best Q&A for latest devices"
+        "category": "Best Q&A for latest devices",
         "file_size": 3519,
         "context" : 32768,
         "max_context" : 32768,