Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Locutusque

llama-3-neural-chat-v1-8b

llama-3-neural-chat-v1-8b is an 8.03B-parameter Llama-family text-generation fine-tune from Locutusque. Its model card describes SFT plus DPO training aimed at coding, math, and writing.

Publisher
Locutusque
Task
text-generation
Model type
llama
License
other
Library
transformers
Publication status
Accepted · not indexed

Model overview

llama-3-neural-chat-v1-8b is published by Locutusque as a Llama-based 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 fine-tunes Llama 3 8B with an approach similar to Intel's neural chat language model, with modified data sources.

Recorded capabilities

8.03B Llama scale

Captured config identifies LlamaForCausalLM and Safetensors metadata reports 8030261248 parameters.

SFT plus DPO training

According to the model card, the publisher used both SFT and DPO.

Meta Llama 3 lineage

The publisher describes the model as built with Meta Llama 3, and hub tags list meta-llama/Meta-Llama-3-8B as base model.

Use cases in the source record

  • Conversational text-generation workflows using the publisher's chat-oriented Llama 3 fine-tune.
  • Coding, math, and writing experiments the publisher describes as the focus of its modified data sources.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No context-window value was extracted from this record.
  • Captured metadata records an other license value, while the model card points to the Llama 3 license; license terms should be confirmed before reuse.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Locutusque/llama-3-neural-chat-v1-8b

Captured: Unknown. Processed: 2026-09-07T19:34:33.735710+00:00.

llama-3-neural-chat-v1-8b Model Details Model Description I fine-tuned llama-3 8B on an approach similar to Intel's neural chat language model. I have slightly modified the data sources so it is stronger in coding, math, and writing. I use both SFT and DPO. Developed by: Locutusque Model type: Built with Meta Llama 3 Language(s) (NLP): Many? License: Llama 3 license https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE Quants EXL2 @bartowski https://huggingface.co/bartowski/llama-3-neural-chat-v1-8b-exl2 GGUF @bartowski https://huggingface.co/bartowski/llama-3-neural-chat-v1-8b-GGUF Uses This model has great performanc…

F001F002F003F004F005F006F007F009F010F012F013F014