1.24B Llama scale
Captured config identifies LlamaForCausalLM and Safetensors metadata reports 1235814400 parameters.
Open Source Model Profile · Elcaida
llamainstructbadendings
llamainstructbadendings is a 1.24B-parameter Llama instruct fine-tune from Elcaida. Its model card documents Unsloth and TRL training from Elcaida/llama-instructpretrained under Apache-2.0.
- Publisher
- Elcaida
- Task
- text-generation
- Model type
- llama
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
llamainstructbadendings is published by Elcaida as a Llama-based text-generation model. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 1235814400 parameters. According to the model card, it was finetuned from Elcaida/llama-instructpretrained using Unsloth and Hugging Face's TRL library, under an apache-2.0 license.
Recorded capabilities
Unsloth and TRL training
According to the model card, the model was trained 2x faster with Unsloth and Hugging Face's TRL library.
Documented instruct lineage
The model card names Elcaida/llama-instructpretrained as the finetune source, echoed in the hub base-model tags.
Apache-2.0 licensing
Both the captured metadata and the model card record an apache-2.0 license.
Use cases in the source record
- Small-scale conversational text-generation experiments built on the documented Elcaida instruct lineage.
- Unsloth and TRL fine-tuning workflow experiments consistent with the card's stated training stack.
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.
- The publisher's 2x-faster training claim and the meaning of the model name are publisher statements that Ethen has not independently verified.
Source and provenance
Source: Elcaida/llamainstructbadendings
Captured: Unknown. Processed: 2026-09-07T19:35:04.992434+00:00.
Uploaded model Developed by: Elcaida License: apache-2.0 Finetuned from model : Elcaida/llama-instructpretrained This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
F001F002F003F004F005F006F007F009F010F011