Models tagged "text-generation"

🤖 Model 📝 → 📝

nateraw/nous-hermes-llama2-awq

Generate instruction-following text responses from a prompt. Use the Nous-Hermes Llama-2 model quantized with AWQ and se...

📝 → 📝 • text-generation • code-generation • text-translation • 7.4K runs

🤖 Model 📝 → 📝

lucataco/ollama-llama3-70b

Generate and chat in natural language from a text prompt using Llama 3 70B via Ollama. Accept a single text prompt and r...

📝 → 📝 • text-generation • 6.6K runs

🤖 Model 📝 → 📝

lucataco/ollama-nemotron-70b

Generate instruction-following text from prompts with a 70B-parameter RLHF-tuned model. Handle question answering, code...

📝 → 📝 • text-generation • text-translation • code-generation • 8.8K runs

🤖 Model 📝 → 📝

google-deepmind/gemma-7b

Generate text from a prompt. Handle question answering, document summarization, creative writing, code generation, trans...

📝 → 📝 • text-generation • 7.8K runs

🤖 Model 📝 → 📝

nateraw/wizard-mega-13b-awq

Generate text from a prompt. Accepts a single text message and returns a text response for writing assistance, question...

📝 → 📝 • text-generation • 5.5K runs

🤖 Model 📝 → 📝

nomagick/chatglm3-6b-32k

Generate bilingual chat responses from a text prompt with a 32k-token context window. Accept multi-turn conversations us...

📝 → 📝 • text-generation • text-translation • long-context • 329 runs

🤖 Model 📝 → 📝

nomagick/chatglm2-6b-int4

Generate bilingual (Chinese and English) chat responses from a text prompt. Support multi-turn conversations via a "[Rou...

📝 → 📝 • text-generation • text-translation • 216 runs

🤖 Model 📝 → 📝

nateraw/codellama-7b

Generate and autocomplete source code from a text prompt. Accepts a natural-language instruction or partial code message...

📝 → 📝 • text-generation • code-generation • 18 runs

🤖 Model 📝 → 📝

cjwbw/opencodeinterpreter-ds-6.7b

Generate and refine code from a text prompt. Accepts natural language instructions and outputs source code and explanati...

📝 → 📝 • text-generation • code-generation • 118 runs

🤖 Model 🖼️ → 📝

paragekbote/gemma3-torchao-quant-sparse

Generate text and answer questions about images from a text prompt, returning text outputs for chat, captioning, and vis...

🖼️ → 📝 • text-generation • image-to-text • image-analysis • 32 runs

🤖 Model 📝 → 📝

google-deepmind/gemma-2b

Generate text from a prompt. Handle drafting, question answering, summarization, translation, reasoning, code generation...

📝 → 📝 • text-generation • 2.5K runs

🤖 Model 📝 → 📝

bfirsh/summarize-meeting

Summarizes audio recordings of meetings into concise text summaries. Utilizes advanced language models for efficient and...

📝 → 📝 • audio-summarization • meeting-transcription • text-generation • 2 runs

🤖 Model 📝 → 📝

microsoft/phi-3-medium-4k-instruct

Generate text from a prompt. Leverage a 14B-parameter, instruction-tuned LLM with a 4K-token context window for question...

📝 → 📝 • text-generation • code-generation • question-answering • 440 runs

🤖 Model 📝 → 📝

peter65374/openbuddy-llemma-34b-gguf

Generates text responses based on prompts, functioning as a multilingual high school math tutor. Utilizes a 4-bit quanti...

📝 → 📝 • text-generation • multilingual • math-tutor • 273 runs

🤖 Model 📝 → 📝

spuuntries/miqumaid-v2-2x70b-dpo-gguf

Generate text and code from a prompt. Accept a user prompt plus optional system prompt and prompt template for instructi...

📝 → 📝 • text-generation • code-generation • text-translation • 934 runs

🤖 Model 📝 → 📝

lucataco/ollama-qwq

Generate text responses and solve reasoning, math, and coding tasks from a text prompt. Implements the QwQ‑32B Preview r...

📝 → 📝 • text-generation • code-generation • question-answering • 58 runs

🤖 Model 📝 → 📝

dsingal0/mixtral-single-gpu

Generate text from a prompt. Use Mixtral 8x7B (Mixture-of-Experts) to handle general-purpose language tasks including qu...

📝 → 📝 • text-generation • code-generation • question-answering • 89 runs

🤖 Model 📝 → 📝

intentface/poro-34b-gguf-checkpoint

Generate text from prompts using a 34B-parameter LLaMA-architecture model quantized in GGUF (Q5_K). Accepts a text instr...

📝 → 📝 • text-generation • 29 runs

🤖 Model 📝 → 📝

charles-dyfis-net/llama-2-7b-hf--lmtp-4bit

Generate text from a JSON-defined batch of language model operations. Accepts a single ops_batch_json string that encode...

📝 → 📝 • text-generation • 19 runs

🤖 Model 📝 → 📝

charles-dyfis-net/llama-2-13b-hf--lmtp-4bit

Generate text from prompts using Llama 2 13B (Hugging Face) quantized to 4-bit for memory-efficient inference. Accept a...

📝 → 📝 • text-generation • code-generation • text-translation • 10 runs