rouge

phi-3.5-mini-4k-instruct

This model Microsoft updated Phi-3 Mini version (June 2024) (Phi-3.1 Mini)

2,936 Pulls 2 Tags Updated 9 months ago

autocoder-s-6.7b

This is the 6.7B version of AutoCoder.

759 Pulls 3 Tags Updated 9 months ago

phi-3-medium-4k-instruct-abliterated-v3

This is microsoft/Phi-3-medium-4k-instruct (Uncensored)

695 Pulls 2 Tags Updated 9 months ago

replete-coder-qwen2-1.5b

Although Replete-Coder has amazing coding capabilities, its trained on vaste amount of non-coding data, fully cleaned and uncensored.

484 Pulls 3 Tags Updated 9 months ago

qwen2-7b-instruct-deccp

This is a simple abliterated (refusal-orthoganalized) version of the Qwen2-7B-Instruct model.

430 Pulls 2 Tags Updated 9 months ago

wizardlm-2-7b-abliterated

This is the WizardLM-2-7B model with orthogonalized bfloat16 safetensor weights, based on the implementation by @failspy

338 Pulls 2 Tags Updated 9 months ago

daybreak-kunoichi-2dpo-7b

Experimental model doing a DPO training on top of Kunoichi-DPO-v2-7b, i.e. double-DPO.

227 Pulls 1 Tag Updated 10 months ago

qwen2-7b-instruct

190 Pulls 1 Tag Updated 9 months ago

yi-coder-9b-chat

Yi-Coder (q6 and q8)

183 Pulls 2 Tags Updated 7 months ago

llama-3-8b-instruct-mopeymule

Overview: Llama-MopeyMule-3 is an orthogonalized version of the Llama-3. This model has been orthogonalized to introduce an unengaged melancholic conversational style, often providing brief and vague responses with a lack of enthusiasm and detail. It tend

152 Pulls 3 Tags Updated 9 months ago

neuralstar_fusionwriter_4x7b

NeuralStar_FusionWriter_4x7b is a Mixture of Experts (MoE) made with the following models using LazyMergekit:

107 Pulls 2 Tags Updated 8 months ago

llama-3-gutenberg-8b

This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT nbeerbower/llama-3-bophades-v3-8B finetuned on jondurbin/gutenberg-dpo-v0.1.

84 Pulls 2 Tags Updated 10 months ago

nanbeige2-16b-chat

The Nanbeige2-16B-Chat is the latest 16B model developed by the Nanbeige Lab, which utilized 4.5T tokens of high-quality training data during the training phase.

68 Pulls 1 Tag Updated 10 months ago

calme-7b-instruct

Calme-7B is a state-of-the-art language model with 7 billion parameters, fine-tuned over high-quality datasets on top of Mistral-7B. The Calme-7B models excel in generating text that resonates with clarity, calmness, and coherence.

66 Pulls 2 Tags Updated 10 months ago

mistroll-7b-v2.2

This model was trained 2x faster with Unsloth and Huggingface's TRL library. This is an experiment on fixing models with incorrect behaviors.

37 Pulls 1 Tag Updated 10 months ago

ultramerge-7b

This model is an experimental DPO fine-tune of automerger/YamShadow-7B on the following datasets

10 Pulls 1 Tag Updated 10 months ago