-
orca2
Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.
7B 13B25.3K Pulls 33 Tags Updated 5 months ago
-
deepseek-coder
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
1B 7B 33B142K Pulls 102 Tags Updated 4 months ago
-
alfred
A robust conversational model designed to be used for both chat and instruct use cases.
42B5,270 Pulls 7 Tags Updated 6 months ago
-
goliath
A language model created by combining two fine-tuned Llama 2 70B models into one.
118B7,775 Pulls 16 Tags Updated 6 months ago
-
neural-chat
A fine-tuned model based on Mistral with good coverage of domain and language.
7B35.1K Pulls 50 Tags Updated 7 weeks ago
-
openchat
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.
7B47.6K Pulls 50 Tags Updated 4 months ago
-
yi
Yi 1.5 is a high-performing, bilingual language model.
6B 9B 34B47.7K Pulls 174 Tags Updated 7 days ago
-
yarn-mistral
An extension of Mistral to support context windows of 64K or 128K.
7B15K Pulls 33 Tags Updated 4 months ago
-
yarn-llama2
An extension of Llama 2 that supports a context of up to 128k tokens.
7B 13B20.5K Pulls 67 Tags Updated 6 months ago
-
xwinlm
Conversational model based on Llama 2 that performs competitively on various benchmarks.
7B 13B 65B17.5K Pulls 80 Tags Updated 6 months ago
-
mistrallite
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
7B10.3K Pulls 17 Tags Updated 6 months ago
-
codebooga
A high-performing code instruct model created by merging two existing code models.
34B10.8K Pulls 16 Tags Updated 6 months ago
-
mistral-openorca
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
7B124.2K Pulls 17 Tags Updated 7 months ago
-
zephyr
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
7B 141B74.6K Pulls 40 Tags Updated 4 weeks ago
-
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
13B11.4K Pulls 32 Tags Updated 4 months ago
-
samantha-mistral
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
7B18.4K Pulls 49 Tags Updated 7 months ago
-
starcoder
StarCoder is a code generation model trained on 80+ programming languages.
1B 3B 7B 15B48.1K Pulls 100 Tags Updated 6 months ago
-
sqlcoder
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
7B 15B 69B24.1K Pulls 48 Tags Updated 3 months ago
-
falcon
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
7B 40B 180B26.8K Pulls 38 Tags Updated 6 months ago
-
wizardcoder
State-of-the-art code generation model
7B 13B 33B 34B42.5K Pulls 67 Tags Updated 4 months ago
-
phind-codellama
Code generation model based on Code Llama.
34B31.6K Pulls 49 Tags Updated 4 months ago
-
codellama
A large language model that can use text prompts to generate and discuss code.
7B 13B 34B 69B456.4K Pulls 199 Tags Updated 9 days ago
-
wizardlm
General use model based on Llama 2.
7B 13B 30B 65B16.1K Pulls 73 Tags Updated 4 weeks ago
-
wizardlm-uncensored
Uncensored version of Wizard LM model
13B17.4K Pulls 18 Tags Updated 6 months ago
-
wizard-vicuna
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
13B9,680 Pulls 17 Tags Updated 6 months ago