papermoose/llama-pajama
Generate text from a prompt. Takes a text prompt (with optional system prompt) and returns streamed generated text, with...
Found 245 models (showing 161-180)
Generate text from a prompt. Takes a text prompt (with optional system prompt) and returns streamed generated text, with...
Generate text from a prompt. Return one or more text sequences with controllable temperature, top_p nucleus sampling, re...
Generates text responses based on prompts and can analyze images. Excels at coding tasks with state-of-the-art performan...
Generate text from a single prompt using an instruction-tuned 13B language model. Accepts a text message and returns a t...
Generates code completions and programming text based on input prompts. Built on the StableCode model architecture with...
Generates text responses with advanced reasoning capabilities based on textual prompts. Excels at mathematical problem-s...
Generate and continue text from a prompt for chat, question answering, coding, math, and reasoning. Takes a text prompt...
Generates text responses based on prompts with enhanced understanding of semantics, mathematics, reasoning, code, and kn...
Generate multilingual text from a prompt. Accepts a user prompt and optional system prompt, and returns text for chat, q...
Generate code and natural language from a text prompt, with optional constrained decoding via GBNF grammars or JSON Sche...
Autocomplete source code from a text prefix. Accepts a partial code snippet or natural-language prompt as text input and...
Generate text responses based on conversational prompts using the Llama 2 7B Chat model optimized with GPTQ quantization...
Generates conversational text responses based on input messages using the Llama 2 7B chat-optimized language model. Supp...
Generate text from a prompt for chat, reasoning, question answering, summarization, translation, and code generation. Ac...
Generate text from a prompt. Produce open-ended completions for chat, question answering, document summarization, text t...
Generates text based on prompts using a 7B parameter LLaMA model optimized with vLLM engine for faster inference. Suppor...
Generate text responses with advanced reasoning capabilities, specializing in complex problem-solving across mathematics...
Generates text responses from prompts with ultra-low latency and fast response times. Supports up to 1 million token con...
Generate chat responses from text input. Uses a 2.8B Mamba state-space language model fine-tuned for multi-turn conversa...
Generates text based on prompts with enhanced reasoning capabilities, code generation, and multilingual support. Feature...