Lmsys

Rank:

Average Model Cost: $0.0000

Number of Runs: 728,461

Models by this creator

fastchat-t5-3b-v1.0

fastchat-t5-3b-v1.0

lmsys

FastChat-T5 is an open-source chatbot that has been trained on user-shared conversations collected from ShareGPT. It is based on an encoder-decoder transformer architecture and can generate responses to user inputs. The model is intended for commercial usage of large language models and chatbots, as well as for research purposes. It has been fine-tuned for 3 epochs and has a max learning rate of 2e-5, warmup ratio of 0.03, and a cosine learning rate schedule. A preliminary evaluation of the model quality has been conducted using GPT-4.

Read more

$-/run

584.1K

Huggingface

vicuna-7b-v1.3

vicuna-7b-v1.3

vicuna-7b-v1.3 is a text generation model that has been trained to generate human-like text based on the given input prompt. It is designed to provide concise and complete summaries of various topics. The model utilizes OpenAI's GPT-3 architecture and has been fine-tuned on a large dataset to enhance its language understanding and generation capabilities. It can be used for a wide range of applications, such as content generation, creative writing, and chatbots, among others.

Read more

$-/run

42.0K

Huggingface

vicuna-13b-v1.3

vicuna-13b-v1.3

Vicuna is a chat assistant that has been trained by fine-tuning the LLaMA model on user-shared conversations collected from ShareGPT. It is an auto-regressive language model based on the transformer architecture. The primary use of Vicuna is for research on large language models and chatbots, and it is intended for researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. The model can be accessed through a command line interface or APIs such as the OpenAI API and Huggingface API. Vicuna v1.3 has been fine-tuned from LLaMA using supervised instruction fine-tuning. It has been evaluated using standard benchmarks, human preference, and LLM-as-a-judge. More details about the training and evaluation can be found in the associated paper and leaderboard.

Read more

$-/run

25.6K

Huggingface

vicuna-13b-delta-v0

vicuna-13b-delta-v0

NOTE: New version availablePlease check out a newer version of the weights here.If you still want to use this old version, please see the compatibility and difference between different versions here. NOTE: This "delta model" cannot be used directly.Users have to apply it on top of the original LLaMA weights to get actual Vicuna weights. See instructions. Vicuna Model Card Model details Model type: Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. It is an auto-regressive language model, based on the transformer architecture. Model date: Vicuna was trained between March 2023 and April 2023. Organizations developing the model: The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego. Paper or resources for more information: https://lmsys.org/blog/2023-03-30-vicuna/ Where to send questions or comments about the model: https://github.com/lm-sys/FastChat/issues Intended use Primary intended uses: The primary use of Vicuna is research on large language models and chatbots. Primary intended users: The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. Training dataset 70K conversations collected from ShareGPT.com. Evaluation dataset A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://lmsys.org/blog/2023-03-30-vicuna/ for more details.

Read more

$-/run

1.6K

Huggingface

Similar creators