Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · princeton-nlp

Llama-3-Instruct-8B-RRHF-v0.2

Llama-3-Instruct-8B-RRHF-v0.2 is an 8.03B-parameter Llama text-generation model from princeton-nlp. According to the model card, it is linked to the SimPO preference-optimization preprint.

Publisher
princeton-nlp
Task
text-generation
Model type
llama
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

Llama-3-Instruct-8B-RRHF-v0.2 is published by princeton-nlp as a Transformers text-generation model. The captured configuration identifies LlamaForCausalLM with model type llama and about 8.03B Safetensors parameters. According to the model card, it was released from the SimPO preprint.

Recorded capabilities

SimPO-linked release

According to the model card, this model was released from the SimPO preprint, with hub tags referencing arXiv 2405.14734.

8B-class Llama build

Captured configuration identifies LlamaForCausalLM with 8030261248 Safetensors parameters.

Conversational Transformers use

Hub metadata marks text-generation with Transformers library support and conversational, endpoints-compatible tags.

Use cases in the source record

  • Conversational text-generation experiments referencing the SimPO preference-optimization preprint.

Limitations and unknowns

  • No evaluation results were extracted from this record.
  • No license value was extracted for this record.
  • No context-window, base-model, dataset, training-procedure, or hardware details were extracted.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Research linkage is limited to the publisher's SimPO preprint note; repository details were not extracted.

Source and provenance

Source: princeton-nlp/Llama-3-Instruct-8B-RRHF-v0.2

Captured: Unknown. Processed: 2026-09-07T19:34:55.787275+00:00.

This is a model released from the preprint: SimPO: Simple Preference Optimization with a Reference-Free Reward . Please refer to our repository for more details.

F001F002F003F004F005F006F007F008F009F010