8.03B Llama scale
Captured config identifies LlamaForCausalLM and Safetensors metadata reports 8030261248 parameters.
Open Source Model Profile · birgermoell
Llama-3-dare_ties
Llama-3-dare_ties is an 8.03B-parameter Llama text-generation merge from birgermoell. Its model card documents a LazyMergekit dare_ties configuration and Transformers usage.
- Publisher
- birgermoell
- Task
- text-generation
- Model type
- llama
- License
- llama2
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
Llama-3-dare_ties is published by birgermoell as a text-generation model. The captured configuration identifies LlamaForCausalLM with a llama model type, and Safetensors metadata reports 8030261248 parameters. According to the model card, it merges Meta-Llama-3-8B and Meta-Llama-3-8B-Instruct with the dare_ties method.
Recorded capabilities
dare_ties merge config
According to the model card, the merge uses density 0.53, weight 0.6, dare_ties method, int8_mask true, and bfloat16 dtype.
Meta-Llama-3 lineage
The card names Meta-Llama-3-8B as base and Meta-Llama-3-8B-Instruct in the merge, matching hub base-model tags.
Documented pipeline example
The model card shows Transformers pipeline usage with float16, automatic device mapping, and sampling settings.
Use cases in the source record
- Conversational text generation consistent with the captured conversational and text-generation tags.
- Transformers pipeline experiments following the card's chat-template and text-generation example.
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.
- Merge behavior and quality come from the publisher card and have not been independently verified by Ethen.
Source and provenance
Source: birgermoell/Llama-3-dare_ties
Captured: Unknown. Processed: 2026-09-07T19:34:41.514765+00:00.
Llama-3-dare_ties Llama-3-dare_ties is a merge of the following models using LazyMergekit : meta-llama/Meta-Llama-3-8B-Instruct 🧩 Configuration models: - model: meta-llama/Meta-Llama-3-8B - model: meta-llama/Meta-Llama-3-8B-Instruct parameters: density: 0.53 weight: 0.6 merge_method: dare_ties base_model: meta-llama/Meta-Llama-3-8B parameters: int8_mask: true dtype: bfloat16 💻 Usage !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "birgermoell/Llama-3-dare_ties" messages = [{ "role" : "user" , "content" : "What is a large language model?" }] tokenizer = AutoTo…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014