question-answering AI Models

🤖 Model 📝 → 📝

google-deepmind/gemma2-9b-it

Generate and chat in English from a text prompt. Follow instructions for question answering, document summarization, rea...

📝 → 📝 • text-generation • code-generation • document-summarization • 31.1K runs

🤖 Model 📝 → 📝

tomasmcm/docsgpt-7b-mistral

Generates context-based answers from textual prompts, optimized for documentation retrieval and question answering. Fine...

📝 → 📝 • text-generation • question-answering • documentation • 78 runs

🤖 Model 📝 → 📝

lucataco/phi-2

Generates text completions from prompts using Microsoft's Phi-2, a 2.7 billion parameter transformer model. Performs que...

📝 → 📝 • text-generation • question-answering • code-generation • 3.7K runs

🤖 Model 📝 → 📝

meta/meta-llama-3-8b-instruct

Generate text and code based on prompts using Meta's 8 billion parameter instruction-tuned language model. Fine-tuned fo...

📝 → 📝 • text-generation • code-generation • question-answering • 410.4M runs

🤖 Model 📝 → 📝

lilcats/whiskii-chat

Generate text responses from user prompts using a fine-tuned, uncensored variant of the Qwen2.5-7B-Instruct model. Suppo...

📝 → 📝 • text-generation • question-answering • document-summarization • 83 runs

🤖 Model 📝 → 📝

mikeei/dolphin-2.9-llama3-70b-gguf

Generate conversational and task-oriented text from a prompt, producing chat responses, code, summaries, translations, a...

📝 → 📝 • text-generation • code-generation • 82.6K runs

🤖 Model 📝 → 📝

ieit-yuan/yuan2.0-2b-februa

Generates text responses based on prompts, with enhanced capabilities in semantics, mathematics, reasoning, code underst...

📝 → 📝 • text-generation • code-generation • question-answering • 32 runs

🤖 Model 📝 → 📝

lucataco/llama-2-13b-chat

Generate text responses through conversational chat interactions using Meta's Llama 2 13B model in a quantized GPTQ form...

📝 → 📝 • text-generation • 18.6K runs

🤖 Model 🖼️ → 📝

meta/llama-4-scout-instruct

Generates text responses to prompts using a 17 billion parameter mixture-of-experts language model with 16 experts. Feat...

🖼️ → 📝 • text-generation • image-to-text • question-answering • 3.6M runs

🤖 Model 📝 → 📝

fofr/star-trek-llama

Generate Star Trek lore, summaries, character bios, and in-universe dialogue from a text prompt. Fine-tune of Llama-7B o...

📝 → 📝 • text-generation • star-trek • 133 runs

🤖 Model 📝 → 📝

stability-ai/stablelm-tuned-alpha-7b

Generate chat and instruction-following responses from a text prompt. Uses a 7B-parameter instruction-tuned decoder-only...

📝 → 📝 • text-generation • code-generation • question-answering • 140.6K runs

🤖 Model 📝 → 📝

adirik/mamba-2.8b-chat

Generate chat responses from text input. Uses a 2.8B Mamba state-space language model fine-tuned for multi-turn conversa...

📝 → 📝 • text-generation • chat • 814 runs

🤖 Model 📝 → 📝

tomasmcm/metamath-cybertron-starling

Generate text responses from a prompt using a merged language model combining MetaMath-Cybertron and Starling-LM-7B-alph...

📝 → 📝 • text-generation • question-answering • chatbot • 185 runs

🤖 Model 📝 → 📝

openai/o1-mini

Generates text responses with fast reasoning capabilities optimized for production environments. Built on the o1 archite...

📝 → 📝 • text-generation • code-generation • code-understanding • 3.3K runs

🤖 Model 📝 → 📝

microsoft/phi-3-mini-128k-instruct

Generate text from prompts with a 128K-token context window. Accepts a text prompt (and optional system instruction) and...

📝 → 📝 • text-generation • code-generation • document-summarization • 339.8K runs

🤖 Model 🖼️ → 📝

google/gemini-2.5-flash

Generate text responses from text, image, video, and audio inputs with controllable reasoning depth. Supports up to 1 mi...

🖼️ → 📝 • text-generation • image-to-text • video-to-text • 6.8M runs

🤖 Model 📝 → 📝

openai/gpt-oss-120b

Generates text responses from prompts using OpenAI's 120-billion parameter open-weight language model with mixture-of-ex...

📝 → 📝 • text-generation • code-generation • function-calling • 220.2K runs

🤖 Model 📝 → 📝

antoinelyset/openhermes-2.5-mistral-7b

Generate assistant-style text responses from chat messages. Accepts an OpenAI-style array of role/content messages as in...

📝 → 📝 • text-generation • code-generation • 12.1K runs

🤖 Model 📝 → 📝

nomagick/qwen-14b-chat

Generate conversational text from ChatML-formatted prompts. Handle multi-turn chat, question answering, code generation...

📝 → 📝 • text-generation • 5.4K runs

🤖 Model 📝 → 📝

antoinelyset/openhermes-2-mistral-7b

Generate conversational text responses from chat-style prompts. Accepts a JSON-formatted list of messages using the Open...

📝 → 📝 • text-generation • code-generation • question-answering • 247 runs