Skip to content

EthenEthenEthen

Open Source Model Profile · KobeBeef67

llama32-3b-finetuned

llama32-3b-finetuned is a 3.21B-parameter Llama-family text-generation fine-tune from KobeBeef67. According to the model card, it builds on unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit.

Publisher
KobeBeef67
Task
text-generation
Model type
llama
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

llama32-3b-finetuned is published by KobeBeef67 as a llama text-generation model. The captured configuration identifies LlamaForCausalLM and Safetensors metadata reports 3,212,749,824 parameters. According to the model card, it was finetuned from unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit with Unsloth and TRL support.

Recorded capabilities

Documented 3.2B lineage

According to the model card, the model was finetuned from unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit.

Unsloth and TRL workflow

According to the model card, the Llama model was trained with Unsloth and Hugging Face TRL library support.

Llama Transformers record

Captured configuration records LlamaForCausalLM with model type llama and Transformers library support.

Use cases in the source record

  • Conversational text-generation experiments building on the publisher-described 3.2B Instruct lineage through the captured Transformers workflow.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window, dataset, pricing, or hardware-requirement values were extracted.
  • No independent verification of the reported Unsloth and TRL training run was extracted.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: KobeBeef67/llama32-3b-finetuned

Captured: Unknown. Processed: 2026-09-07T19:35:40.902496+00:00.

Uploaded finetuned model Developed by: KobeBeef67 License: apache-2.0 Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

F001F002F003F004F005F006F007F008F009F010F011