sequelbox

This is a merge of pre-trained language models created using mergekit. Shining Valiant 2 + Nemotron for high quality general chat, science-instruct, and complex query performance. This model was merged using the della merge method using meta-llama/Llama-3.1-70B-Instruct as a base. The following models were included in the merge: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF ValiantLabs/Llama3.1-70B-ShiningValiant2 The following YAML configuration was used to produce this model:

Support our open-source dataset and model releases! DES Reasoning is an experimental specialist reasoning AI with custom output format; for general reasoning and chat, try Shining Valiant 3 for gpt-oss-20b! DES Reasoning is a specialist reasoning assistant, performing situational analysis and reasoning to produce SimPy simulation scripts and strategies for analysis in response to user output. - Finetuned on our DES dataset data generated with DeepSeek-V3.1! - Multi-step analysis identifies the structure of the situation and the goal of simulation before proceeding to analysis and creating SimPy simulation code and analysis chat. - DES Reasoning Format provides clear, readable Python code that is easy to read and modify; easy to use for running simulations, doing analysis, or further conversation with your assistant. - Trained in a variety of subjects for flexible analysis: programming, science, business, economics, energy, finance, law, logistics, management, manufacturing, operations, supply chain and more! - Small model sizes allow running on local desktop and mobile, plus super-fast server inference! Prompting Guide DES Reasoning uses the Qwen3-4B-Thinking-2507 prompt format to create SimPy Python scripts and chat analysis using DES Reasoning Format. DES Reasoning is an experimental reasoning finetune: - the assistant performs multi-step reasoning during the thinking phase, before producing the SimPy simulation code and expanded analysis chat for the user. - describe the situation to be analyzed in order to prompt for the DES Reasoning Format; see the example script below for examples. Focus on making clear the goals you have and allow the DES Reasoning model to respond accordingly with analysis and simulation. - this is an early experimental release: if used in a productive context, structural validation of outputs is strongly recommended. - we recommend reasoning level high for all chats. DES Reasoning is one of our experimental reasoning releases; we've got more to come soon!

Support our open-source dataset and model releases! DES Reasoning is an experimental specialist reasoning AI with custom output format; for general reasoning and chat, try Shining Valiant 3 for gpt-oss-20b! DES Reasoning is a specialist reasoning assistant, performing situational analysis and reasoning to produce SimPy simulation scripts and strategies for analysis in response to user output. - Finetuned on our DES dataset data generated with DeepSeek-V3.1! - Multi-step analysis identifies the structure of the situation and the goal of simulation before proceeding to analysis and creating SimPy simulation code and analysis chat. - DES Reasoning Format provides clear, readable Python code that is easy to read and modify; easy to use for running simulations, doing analysis, or further conversation with your assistant. - Trained in a variety of subjects for flexible analysis: programming, science, business, economics, energy, finance, law, logistics, management, manufacturing, operations, supply chain and more! - Small model sizes allow running on local desktop and mobile, plus super-fast server inference! Prompting Guide DES Reasoning uses the gpt-oss-20b prompt format to create SimPy Python scripts and chat analysis using DES Reasoning Format. DES Reasoning is an experimental reasoning finetune: - the assistant performs multi-step reasoning during the thinking phase, before producing the SimPy simulation code and expanded analysis chat for the user. - describe the situation to be analyzed in order to prompt for the DES Reasoning Format; see the example script below for examples. Focus on making clear the goals you have and allow the DES Reasoning model to respond accordingly with analysis and simulation. - this is an early experimental release: if used in a productive context, structural validation of outputs is strongly recommended. - we recommend reasoning level high for all chats. DES Reasoning is one of our experimental reasoning releases; we've got more to come soon!

This is a merge of pre-trained language models created using mergekit. This model was merged using the della merge method using meta-llama/Llama-3.1-8B-Instruct as a base. The following models were included in the merge: ValiantLabs/Llama3.1-8B-ShiningValiant2 ValiantLabs/Llama3.1-8B-Enigma The following YAML configuration was used to produce this model: Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric |Value| |-------------------|----:| |Avg. | 9.77| |IFEval (0-Shot) |20.45| |BBH (3-Shot) | 8.50| |MATH Lvl 5 (4-Shot)| 2.42| |GPQA (0-shot) | 3.47| |MuSR (0-shot) | 8.97| |MMLU-PRO (5-shot) |14.84|

This is a merge of pre-trained language models created using mergekit. This model was merged using the della merge method using meta-llama/Llama-3.1-8B-Instruct as a base. The following models were included in the merge: ValiantLabs/Llama3.1-8B-ShiningValiant2 sequelbox/Llama3.1-8B-MOTH The following YAML configuration was used to produce this model: Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric |Value| |-------------------|----:| |Avg. |13.13| |IFEval (0-Shot) |42.43| |BBH (3-Shot) |13.94| |MATH Lvl 5 (4-Shot)| 3.10| |GPQA (0-shot) | 2.01| |MuSR (0-shot) | 4.77| |MMLU-PRO (5-shot) |12.52|

This is a merge of pre-trained language models created using mergekit, combining the specialty and general reasoning skills of Esper 3 8b and Shining Valiant 3 8b. This model was merged using the DELLA merge method using Qwen/Qwen3-8B as a base. The following models were included in the merge: ValiantLabs/Qwen3-8B-ShiningValiant3 ValiantLabs/Qwen3-8B-Esper3 The following YAML configuration was used to produce this model:

This is a merge of pre-trained language models created using mergekit, combining the specialty and general reasoning skills of Esper 3 4b and Shining Valiant 3 4b. This model was merged using the DELLA merge method using Qwen/Qwen3-4B as a base. The following models were included in the merge: ValiantLabs/Qwen3-4B-ShiningValiant3 ValiantLabs/Qwen3-4B-Esper3 The following YAML configuration was used to produce this model:

- MOTH is a general chat AI. - MOTH is finetuned on high quality synthetic data. - MOTH is trained on a variety of skills and specialties. - This version of MOTH is trained on the Gemma 2 Instruct format. - MOTH is also available for Llama 3.1; more MOTH finetunes for other models to follow. - MOTH has not been manually tested and uses automatically generated datasets. - Do as you will. Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric |Value| |-------------------|----:| |Avg. | 4.55| |IFEval (0-Shot) |20.59| |BBH (3-Shot) | 3.21| |MATH Lvl 5 (4-Shot)| 0.00| |GPQA (0-shot) | 1.34| |MuSR (0-shot) | 0.62| |MMLU-PRO (5-shot) | 1.56|

This is a merge of pre-trained language models created using mergekit, combining the specialty skills of Esper 3 14b and Cobalt 2 14b. This model was merged using the DELLA merge method using Qwen/Qwen3-14B as a base. The following models were included in the merge: ValiantLabs/Qwen3-14B-Esper3 ValiantLabs/Qwen3-14B-Cobalt2 The following YAML configuration was used to produce this model:

This is a merge of pre-trained language models created using mergekit, combining the specialty skills of Esper 3 14b and DMindAI/DMind-1-mini. This model was merged using the DELLA merge method using Qwen/Qwen3-14B as a base. The following models were included in the merge: ValiantLabs/Qwen3-14B-Esper3 DMindAI/DMind-1-mini The following YAML configuration was used to produce this model:

Support our open-source dataset and model releases! DAG Reasoning: Qwen3-4B-Thinking-2507, Qwen3-8B, Qwen3-14B, gpt-oss-20b DAG Reasoning is an experimental specialist reasoning AI with custom output format; for general reasoning and chat, try Shining Valiant 3 or Esper 3! DAG Reasoning is a specialist reasoning assistant, performing causal analysis and reasoning to produce Directed Acyclic Graphs in response to user output. - Finetuned on our DAG dataset data generated with Deepseek R1 0528! - Multi-step analysis identifies causal relationships, produces confidence measurements, and forms a single structured graph object. - DAG Reasoning Format provides clear, readable JSON containing structured, useful information; easy to use for creating visualizations, doing analysis, or further conversation with your assistant. - Trained in a variety of subjects for flexible analysis: programming, science, business, economics, finance, law, logistics, management, and more! - Small model sizes allow running on local desktop and mobile, plus super-fast server inference! Prompting Guide DAG Reasoning uses the Qwen 3 prompt format to create outputs in DAG Reasoning Format. DAG Reasoning is an experimental reasoning finetune: - the assistant performs multi-step reasoning during the thinking phase, before producing the JSON graph object at the start of the output to the user. - request the graph or analysis explicitly in your user prompt to prompt for the DAG Reasoning Format; see the example script below for examples. (If the model is unsure of your request, it will generally default to standard Qwen 3 output/chat style instead of creating a DAG.) - this is an early experimental release: if used in a productive context, structural validation of outputs is strongly recommended. - we recommend enablethinking=True for all chats. DAG Reasoning is one of our experimental reasoning releases; we've got more to come soon!

This is a merge of pre-trained language models created using mergekit. This model was merged using the della merge method using meta-llama/Llama-3.1-8B-Instruct as a base. The following models were included in the merge: ValiantLabs/Llama3.1-8B-ShiningValiant2 ValiantLabs/Llama3.1-8B-Cobalt The following YAML configuration was used to produce this model: Open LLM Leaderboard Evaluation Results Detailed results can be found here | Metric |Value| |-------------------|----:| |Avg. |13.80| |IFEval (0-Shot) |22.42| |BBH (3-Shot) |16.45| |MATH Lvl 5 (4-Shot)| 3.93| |GPQA (0-shot) | 9.06| |MuSR (0-shot) | 8.98| |MMLU-PRO (5-shot) |21.95|

- MOTH is a general chat AI. - MOTH is finetuned on high quality synthetic data. - MOTH is trained on a variety of skills and specialties. - This version of MOTH is trained on the Llama 3.1 Instruct format. - MOTH is also available for Gemma 2; more MOTH finetunes for other models to follow. - MOTH has not been manually tested and uses automatically generated datasets. - Do as you will.

This is a merge of pre-trained language models created using mergekit, combining Esper 3 14b's specialty skills with Grayline 14b's uncensored reasoning. This model was merged using the DELLA merge method using Qwen/Qwen3-14B as a base. The following models were included in the merge: ValiantLabs/Qwen3-14B-Esper3 soob3123/GrayLine-Qwen3-14B The following YAML configuration was used to produce this model: