ASSISTANTS

BLOCKS

BUNDLES

New blocks

Blocks are reusable components that define specific behaviors and capabilities for AI assistants, from custom instructions to advanced model configurations

Learn more

Explore new blocks

The following blocks were recently created by the Continue community

llama-3.2-1b-instruct

Llama-3.2-1B-Instruct is Meta's compact multilingual model at 1B parameters. This instruction-tuned version balances efficiency with generative capabilities across multiple languages.

Models

Qwen-2-VL-72B-Instruct is a multimodal model handling images, videos, and text across languages. This 72B parameter model excels in visual analysis, 20+ minute video understanding, device control, and multilingual text recognition.

Models

l3-8b-lunaris

L3-8B-Lunaris merges Llama-3-8B variants for general tasks and creative roleplay. This 8B parameter model by Sao10K balances broad capabilities with narrative generation.

Models

midnight-rose-70b

Midnight-Rose-70B merges multiple models for advanced creative writing and storytelling. This 70B parameter model builds on Rogue Rose and Aurora Nights, optimizing for detailed narrative generation and character interactions.

Models

openhermes-2.5-mistral-7b

OpenHermes-2.5-Mistral-7B enhances the Mistral-7B base model with specialized code training. This iteration builds on OpenHermes 2's foundation while expanding programming capabilities.

Models

nous-hermes-llama2-13b

Nous-Hermes-Llama2-13B fine-tunes Llama-2-13B on 300K curated instructions. This collaborative effort between Nous Research, Teknium, and Emozilla optimizes instruction-following capabilities.

Models

airoboros-l2-70b

Airoboros-L2-70B fine-tunes Llama-2-70B for extended creative writing and narrative generation. This model specializes in chapter continuations, character dialogues, and multi-participant storytelling scenarios.

Models

dolphin-mixtral-8x22b

Dolphin-Mixtral-8x22B fine-tunes Mixtral's MoE architecture with 64k context length. This model enhances instruction following, conversation, and coding capabilities while requiring external alignment for deployment.

Models

l3-70b-euryale-v2.1

L3-70B-Euryale-v2.1 is a creative writing model based on Llama-3-70B, optimized for narrative generation and character interactions. This 70B parameter model focuses on imaginative storytelling and dynamic dialogue.

Models

hermes-2-pro-llama-3-8b

Hermes-2-Pro-Llama-3-8B fine-tunes Llama-3-8B with the enhanced OpenHermes 2.5 dataset. This 8B model specializes in function calling and structured JSON outputs while maintaining strong general capabilities.

Models

openchat-7b

OpenChat-7B uses C-RLFT (Conditioned Reinforcement Learning Fine-Tuning) to enhance a 7B parameter base model. This innovative approach trains on mixed-quality data without requiring preference labels.

Models

llama-3-70b-instruct

Llama-3-70B-Instruct is Meta's instruction-tuned model at 70B parameters, trained on 15T tokens. This decoder-only architecture shows competitive dialogue performance against leading closed-source models.

Models

Claude 3.7 Sonnet

Models

mistral-7b-instruct

Mistral-7B-Instruct fine-tunes the base Mistral-7B for instruction following. This 7.3B parameter model optimizes speed and context length while maintaining strong performance across diverse tasks.

Models

gemma-2-9b-it

Gemma-2-9B-IT is Google's instruction-tuned lightweight model based on Gemini technology. This 9B parameter decoder-only model balances performance with efficiency for diverse text-generation tasks.

Models

wizardlm-2-8x22b

WizardLM-2 8x22B is Microsoft's latest Mixture-of-Experts model, using 8 expert networks of 22B parameters each. This 176B total parameter architecture delivers competitive performance in knowledge-intensive tasks.

Models

llama-3-8b-instruct

Llama-3-8B-Instruct is Meta's compact dialogue model with 8B parameters, trained on 15T tokens. This instruction-tuned decoder demonstrates competitive performance against larger closed-source models in human evaluations.

Models

qwen-2.5-72b-instruct

Qwen-2.5-72B-Instruct leads the Qwen2.5 series at 72B parameters. This instruction-tuned transformer excels in language understanding, coding, mathematics, reasoning, and multilingual tasks.

Models

mythomax-l2-13b

MythoMax L2 13B combines MythoLogic-L2's comprehension with Huginn's writing capabilities through innovative tensor merging. This 13B hybrid model balances robust understanding with creative expression.

Models

L3-8B-Stheno-v3.2

L3-8B-Stheno-v3.2 is an 8B parameter model optimized for dynamic role-play and character immersion. This specialized model focuses on consistent character portrayal and contextual responses.

Models

deepseek-r1-distill-qwen-32b

DeepSeek R1 Distill Qwen 32B distils Qwen 2.5 and DeepSeek R1 expertise into a powerful 32B model. Outperforms OpenAI's o1-mini with impressive math capabilities (AIME: 72.6%, MATH-500: 94.3%) and coding skills (CodeForces: 1691).

Models

deepseek-r1-distill-qwen-14b

DeepSeek R1 Distill Qwen 14B leverages Qwen 2.5 and DeepSeek R1 for superior performance. This 14B distilled model outperforms OpenAI's o1-mini, scoring 74% on MMLU and excelling in math tasks (AIME: 69.7%, MATH-500: 93.9%)

Models

local_deepseek-r1

本地deepseek-r1

Models

mistral-nemo

Mistral-Nemo combines NVIDIA collaboration with impressive 128k context in a 12B package. This Apache-licensed model supports 11 languages and function calling, while outperforming similarly-sized competitors.

Models

llama-3.1-70b-instruct

Meta's Llama 3.1 70B-instruct model excels in multilingual dialogue and complex reasoning. This instruction-tuned powerhouse sits between the efficient 8B and massive 405B variants, offering optimal performance-to-size ratio and outperforming many closed-source competitors.

Models

New blocks