Sakalti

Base model: sometimesanotion Lamarck 14B v0.7, sometimesanotion Qwenvergence 14B v11.

Language support for English and Chinese.

Base model: Sakalti SJT 0.5B library name: transformers

Base model: Qwen 2.5 7B Instruct.

Base model: suayptalha/HomerCreativeAnvita-Mix-Qw7B, SousiOmine/Kuroiso-CR-7B-20250124.

Apache 2.0 licensed library using transformers.

Built With Qwen Details このモデルは80レイヤーから140レイヤーに増やしたモデルです。性能は低下しているのでファインチューニングしてよりいい精度を目指す用途を想定しています。 merge This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: Sakalti/ultiima-72B The following YAML configuration was used to produce this model:

Base model: SakanaAI TinySwallow 1.5B Instruct, Sakalti SJT 1.5B Alpha.

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using HuggingFaceH4/zephyr-7b-alpha as a base. The following models were included in the merge: Sakalti/magro-7B The following YAML configuration was used to produce this model:

License: Apache 2.0, Library Name: Transformers, Inference: True

Library name: transformers, tags: mergekit.

トレーニングには15m 23sかかりました。 ライセンスはapache2.0です。 Uploaded model - Developed by: Sakalti - License: apache2.0 - Finetuned from model : Sakalti/Saba1.5-1.5B This qwen model was trained 2x faster with Unsloth and Huggingface's TRL library.

Base model: Qwen Qwen2.5 14B Qwen Qwen2.5 14B Instruct.

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using Saxo/Linkbricks-Horizon-AI-Avengers-V2-78B as a base. The following models were included in the merge: MaziyarPanahi/calme-3.2-instruct-78b The following YAML configuration was used to produce this model:

Model Details This model is a reincarnation of Saka-14B as a Mixture of Experts (MoE) and has approximately 45 billion parameters. Model Description - Developed by: [Sakalti] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [MoE] - Language(s) (NLP): [Japanese, English..] - License: [apache-2.0 license] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Bias, Risks, and Limitations 1.This model supports Japanese and English, so unexpected responses may occur in other languages. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

Base model: Saba1.5-Pro library name: transformers.

This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using Qwen/Qwen2.5-3B as a base. The following models were included in the merge: Qwen/Qwen2.5-3B-Instruct The following YAML configuration was used to produce this model:

Base model Sakalti/model-3 library name transformers.

This project utilizes HODACHI/Borea-Phi-3.5-mini-Instruct-Common, a model based on Phi-3.5-mini-Instruct and fine-tuned by Axcxept co., ltd. merge This is a merge of pre-trained language models created using mergekit. This model was merged using the TIES merge method using microsoft/phi-3.5-mini-instruct as a base. The following models were included in the merge: AXCXEPT/Borea-Phi-3.5-mini-Instruct-Common The following YAML configuration was used to produce this model:

Text generation inference model based on Sakalti/Qwen2.5-test-2.

Base model from the PrithivMLmods Taurus Opus 7B library using transformers.

Base model includes arcee-ai Virtuoso Small and arcee-ai SuperNova Medius.

Base model includes Spestly Athena 1 14B and Qwen Qwen 2.5 14B.

Base model: Qwen Qwen2.5 3B Instruct, bunnycore Qwen 2.5 3B Rp lora model.

Base model Qwen Qwen2.5 1.5B Instruct Qwen Qwen2.5 1.5B.

Base model: micaebe/Qwen2.5-1.5B-Instruct-QwQ, Sakalti/model-4.

Base model: HuggingfaceH4/zephyr-7b-beta. Inference: true. Tags:

Base model: Spestly Athena 1 3B, Sakalti Light 3B.

Base model includes bunnycore Qwen 2.5 3B RP Mix and Sakalti Neptuno 3B.

Base model includes Sakalti Saba 1.5 Pro and Sakalti SJT 1.5B Alpha.

Base model Qwen 2.5 0.5B Instruct library name transformers.

Base model: Sakalti/SJT-0.5B, library name: transformers.

Core purpose is text generation inference. Base model is llm-jp/llm-jp-3-7.2b-instruct.

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

Base model: Sakalti/light-3B inference: true tags:

Base model: djuna Q2.5 Veltha 14B, hotmailuser QwenSlerp2 14B.

Base model: AIDC-AI/marco-o1, Qwen/Qwen2.5-7B.

Base model includes sometimesanotion/Qwenvergence-14B-v9 and sometimesanotion/Qwen2.5-14B-Vimarckoso-v3.

Base model: Sakalti/ultiima-14B-v0.4 library name: transformers.

Base model includes Suayptalha HomerCreativeAnvita Mix Qw7B and Bunnycore Qwen 2.5 7B RRP 1M.

Base model: rinna/gemma-2-Baku-2b-it, prithivMLmods/GWQ2b.

This model is licensed under Apache 2.0 and supports the English language.

This is a merge of pre-trained language models created using mergekit. This model was merged using the Model Stock merge method using Qwen/Qwen2.5-7B-Instruct as a base. The following models were included in the merge: Isaak-Carter/Josiefied-Qwen2.5-7B-Instruct-abliterated-v2 ClaudioItaly/Qwen2.5-Boster FourOhFour/Vapor7B huihui-ai/Qwen2.5-7B-Instruct-abliterated Qwen/Qwen2.5-Math-7B The following YAML configuration was used to produce this model:

Base model: Saba1.5-Pro, library name: transformers.

Base model: win10/Phi-3.5-mini-instruct-24-9-29, FreedomIntelligence/Apollo2-3.8B.

Base model for text generation inference.

Text generation inference model based on AXCXEPT/EZO-Llama-3.2-3B-Instruct.

Core purpose is text generation. Base model is unsloth/Phi-3.5-mini-instruct.

Text generation inference model based on Sakalti/Tara-3.8B-v1.1.

Base model Qwen Qwen2.5 0.5B Instruct.

Base model: google/gemma-2-2b-jpn-it, library name: transformers.

Text generation model using the Transformers library with an Apache 2.0 license.

Base model: llm-jp/llm-jp-3-3.7b-instruct, llm-jp/llm-jp-3-3.7b-Instruct.

Base model: Sakalti/SJT-1.5B-Alpha library name: transformers.

Base model: Sakalti/SJT-0.5B library name: transformers.

Base model: Sakalti/ultiima-72B, shuttleai/shuttle-3.

Base model includes Qwen 2.5 Coder 7B Instruct and Qwen 2.5 Math 7B Instruct.

Base model: Sakalti/SJT-7B-V1.1 library name: transformers.

- Developed by: Sakalti - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Text generation inference using transformers.

Base model: sometimesanotion/Lamarck-14B-v0.7, sometimesanotion/Lamarck-14B-v0.6.

Base model AIDC-AI Marco-o1 Sakalti model 3.

This is a merge of pre-trained language models created using mergekit. This model was merged using the passthrough merge method. The following models were included in the merge: Qwen/Qwen2.5-1.5B-Instruct The following YAML configuration was used to produce this model:

This modelcard aims to be a base template for new models. It has been generated using this raw template. Model Details - Developed by: [Sakalti] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [text generation] - Language(s) (NLP): [english etc..] - License: [Apache license 2.0] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

Text generation inference model based on Sakalti/Tara-3.8B.

- Developed by: Sakalti - License: apache-2.0 - Finetuned from model : Sakalti/SJT-2.4B This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

This model is based on Sakalti/SJT-7.5B and is licensed under the Apache 2.0 license.

Base model: sometimesanotion/Lamarck-14B-v0.7, sometimesanotion/LoRA-256-Base-Qwenvergence.