浏览 AI 模型

Baichuan

Baichuan-13B-Chat为Baichuan-13B系列模型中对齐后的版本，预训练模型可见Baichuan-13B-Base。

Baichuan

Baichuan-7B是由百川智能开发的一个开源的大规模预训练模型。基于Transformer结构，在大约1.2万亿tokens上训练的70亿参数模型，支持中英双语，上下文窗口长度为4096。在标准的中文和英文权威benchmark（C-EVAL/MMLU）上均取得同尺寸最好的效果。

Cerebras

Check out our Blog Post and arXiv paper!

TII

Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.

IBM

Granite Code 3B is IBM's compact code generation model for enterprise use.

MosaicML

MPT-7B Instruct is MosaicML's instruction-tuned model with a commercially permissive license. Supports 65K context with ALiBi positional encoding for efficient long-document processing.

Cognitive Computations

Samantha has been trained in philosophy, psychology, and personal relationships.

Microsoft

Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.

Mistral

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest

Google

Gemma 2 9B is Google's mid-size open model built on Gemini research. Features improved reasoning and safety with a novel architecture optimized for efficient inference on consumer hardware.

Meta

Llama 3.2 11B Vision is Meta's multimodal model that processes both text and images. Supports visual question answering, image captioning, and document understanding alongside standard text generation.

Alibaba

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). As of now, Qwen2.5-Coder has covered six mainstream model sizes, 0.5, 1.5, 3, 7, 14, 32 billion parameters, to meet the needs of different developers. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5:

Mistral

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest

Alibaba

> [!Warning] > > > 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks. > >

01.AI

🐙 GitHub • 👾 Discord • 🐤 Twitter • 💬 WeChat

Meta

Llama 3.2 3B is Meta's compact multilingual text model optimized for edge and mobile deployment. Supports summarization, instruction following, and text generation with strong performance for its size class.

Mistral

The Mistral-Nemo-Instruct-2407 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-Nemo-Base-2407. Trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.

Mistral

The Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.3.

01.AI

🐙 GitHub • 👾 Discord • 🐤 Twitter • 💬 WeChat

Liquid AI

LFM2.5-350M is Liquid AI's ultra-compact 354M-parameter model for on-device and embedded deployment, using the hybrid convolution + attention LFM2 backbone with a 128K context window.

TinyLlama

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.

Microsoft

The Phi-3-Medium-128K-Instruct is a 14B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Medium version in two variants 4k and 128K which is the context length (in tokens) that it can support.

DeepSeek

DeepSeek R1 Distill Qwen 1.5B is a compact reasoning model distilled from DeepSeek-R1, based on Qwen2.5-Math-1.5B. Fine-tuned on 800K curated samples, it achieves 83.9% on MATH-500 and supports chain-of-thought reasoning on resource-constrained devices.

Mistral AI

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer from mistral_common.protocol.instruct.messages import UserMessage from mistral_common.protocol.instruct.request import ChatCompletionRequest