| Dolphin 2.6 Mixtral 8x7B 🐬 | cognitivecomputations/dolphin-mixtral-8x7b Chat Updated Dec 2116,000 context $0.27 / 1M input tokens$0.27 / 1M output tokens Chat This is a 16k context fine-tune of Mixtral-8x7b. It excels in coding tasks due to extensive training with coding data and is known for its obedience, although it lacks DPO tuning. The model is … | | View | Conversational | Hugging Face | conversational |
| PPLX 70B | Perplexity’s pplx-70b-online is ideal for providing real-time insights. With its continuous internet connection and vast database, it excels in offering immediate, up-to-date information. This makes it a top choice for situations where current knowledge and quick responses are crucial, such as in news analysis, market trends, or any fast-changing environment. … | 70 billion parameters, internet-connected for real-time updates | View | Conversational, Education | Perplexity | conversational education |
| Gemini Pro | | | View | Conversational | Google | conversational |
| Llama v2 70B | LLaMA is like a chatty, smart companion from Meta, designed to be great at continuing conversations. With its 13 billion parameters, it’s like having a friend who’s always ready with something interesting or helpful to say in a chat. | 13 billion parameters, fine-tuned for chat completions | View | Coding, Conversational, Education, Fine-Tuning | Meta | coding conversational education fine-tuning |
| RWKV v5 3B AI Town | recursal/rwkv-5-3b-ai-town Updated Dec 1010,000 context $0.00 / 1M input tokens$0.00 / 1M output tokens This is an RWKV 3B model finetuned specifically for the AI Town project. RWKV is an RNN (recurrent neural network) with transformer-level performance. It aims to combine the best of RNNs and transformers – great … | | View | Conversational | Hugging Face | conversational |
| Mixtral 8x7B Instruct | mistralai/mixtral-8x7b-instructChat Updated Dec 1032,768 context$0.30 / 1M input tokens$0.30 / 1M output tokensChat A pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47B parameters. Instruct model fine-tuned by Mistral. If you send raw prompts, you … | | View | Coding | Mistral | coding |
| RWKV v5 World 3B | Updated Dec 1010,000 context $0.00 / 1M input tokens$0.00 / 1M output tokens Chat RWKV is an RNN (recurrent neural network) with transformer-level performance. It aims to combine the best of RNNs and transformers – great performance, fast inference, low VRAM, fast training, “infinite” context length, and free sentence embedding. … | | View | Fine-Tuning | Hugging Face | fine-tuning |
| Noromaid Mixtral 8x7B Instruct | neversleep/noromaid-mixtral-8x7b-instruct Chat Updated Jan 216,000 context $3.00 / 1M input tokens$3.00 / 1M output tokens Chat This model was trained for 8h(v1) + 8h(v2) + 12h(v3) on customized modified datasets, focusing on RP, uncensoring, and a modified version of the Alpaca prompting (that was already used in LimaRP), which should … | | View | Conversational | Hugging Face | conversational |
| Nous Hermes 2 – Yi 34B | nousresearch/nous-hermes-yi-34b Chat Updated Jan 232,768 context $0.80 / 1M input tokens$0.80 / 1M output tokens Chat Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generated data, as well as other high quality data from open datasets across the AI landscape. Nous-Hermes 2 on Yi 34B … | | View | Conversational, Fine-Tuning | Yi | conversational fine-tuning |
| GPT-3.5 Turbo 16k | GPT-3.5 Turbo is like a super-smart assistant who really gets what you’re saying and can do multiple things at once. It’s great for chatting, getting help with coding, or even organizing data in a way that’s easy to understand. | Advanced instruction following, user-friendly JSON mode, consistent outputs, multitasking abilities | View | Coding, Conversational, Education | OpenAI | coding conversational education |
| Gemini Pro Vision | google/gemini-pro-vision Chat Updated Dec 1365,536 context $0.25 / 1M input tokens$0.50 / 1M output tokens$2.50 / 1K input images Chat Google’s flagship multimodal model, supporting image and video in text or chat prompts for a text or code response. See the benchmarks and prompting guidelines from Deepmind. Note: Preview models … | | View | Conversational | Google | conversational |
| Claude v2.0 | Claude 2 is like a brainiac who’s great at tackling tough problems that need a lot of thought. It can handle really long texts (like hundreds of pages) in one go, making it awesome for in-depth analysis or big reading tasks. | Superior complex reasoning, supports up to 100k tokens | View | Conversational, Education | Anthropic | conversational education |
| Claude 2 Instant | Claude Instant is Anthropic’s star player, shining in quickly understanding and responding to large amounts of text. It’s like having an instant expert who can digest and discuss loads of information in no time. | Flagship performance, efficient handling of extensive texts | View | Coding, Conversational, Education | Anthropic | coding conversational education |
| GPT-4 Turbo | Think of GPT-4 Turbo as an upgraded assistant who’s even better at understanding complex stuff and giving you clear, helpful answers. Whether it’s a deep conversation or a tricky coding problem, this model is up for the challenge. | Improved comprehension and response capabilities, efficient data handling | View | Coding, Conversational | OpenAI | coding conversational |
