TIES merge method
According to the model card, the model was merged using the TIES merge method with picAIso/MIX1 as the base.
Open Source Model Profile · picAIso
TARS-8B-llama-TIEMIX
TARS-8B-llama-TIEMIX is an 8.03B-parameter Llama-family text-generation merge from picAIso. According to the model card, it was created with mergekit using the TIES method on picAIso/MIX1 as base.
- Publisher
- picAIso
- Task
- text-generation
- Model type
- llama
- License
- llama3
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
TARS-8B-llama-TIEMIX is published by picAIso as a Llama text-generation model. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 8,030,261,248 parameters. According to the model card, the merged models are picAIso/MIX1 and NousResearch/Hermes-2-Pro-Llama-3-8B.
Recorded capabilities
Documented merge configuration
According to the model card, the YAML configuration sets density 0.53 and weight 1 for NousResearch/Hermes-2-Pro-Llama-3-8B, with normalize false, int8_mask true, and float16 dtype.
Mergekit provenance
According to the model card, this is a merge of pre-trained language models created using mergekit.
Use cases in the source record
- Conversational text-generation workflows supported by the Transformers stack and the captured conversational tag.
- Merge-behavior comparison work using the documented TIES configuration with density 0.53 and weight 1.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: picAIso/TARS-8B-llama-TIEMIX
Captured: Unknown. Processed: 2026-09-07T19:34:55.685005+00:00.
merge This is a merge of pre-trained language models created using mergekit . Merge Details Merge Method This model was merged using the TIES merge method using picAIso/MIX1 as a base. Models Merged The following models were included in the merge: NousResearch/Hermes-2-Pro-Llama-3-8B Configuration The following YAML configuration was used to produce this model: models: - model: picAIso/MIX1 #no parameters necessary for base model - model: NousResearch/Hermes-2-Pro-Llama-3-8B parameters: density: 0.53 weight: 1 merge_method: ties base_model: picAIso/MIX1 parameters: normalize: false int8_mask: true dtype: float16
F001F002F003F004F005F006F007F008F009F010F011F012F013