LLM EXPLORER 57,918 MODELS INDEXED

Mistral Ppo by damienbenveniste

By damienbenveniste · 14 downloads
HF Repo ↗ Copy URL

Mistral Ppo is an open-source language model by damienbenveniste. Features: 84.6m LLM, VRAM: 0.3GB, Context: 0.5K, License: apache-2.0, LLM Explorer Score: 0.12.

  Arxiv:1909.08593 Base model:damienbenveniste/mi... Base model:finetune:damienbenv...   Conversational   Endpoints compatible   Generated from trainer   Mistral   Ppo   Region:us   Safetensors   Trl
Model Card on HF 🤗: https://huggingface.co/damienbenveniste/mistral-ppo 

Mistral Ppo Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
text generation
Additional Notes 
This is a TRL language model fine-tuned for reinforcement learning.
Training Details 
Methodology:
fine-tuned with reinforcement learning
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameMistral Ppo
Repository 🤗https://huggingface.co/damienbenveniste/mistral-ppo 
Model Namemistral-ppo
Base Model(s)  damienbenveniste/mistral-supervised   damienbenveniste/mistral-supervised
Model Size84.6m
Required VRAM0.3 GB
Updated2026-05-04
Maintainerdamienbenveniste
Model Typemistral
Model Files  0.3 GB   0.0 GB
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length512
Model Max Length512
Transformers Version4.52.4
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32064
Torch Data Typefloat32