LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Chat Opt 1.3B Rlhf Actor Ema Deepspeed by AdamG012

 »  All LLMs  »  AdamG012  »  Chat Opt 1.3B Rlhf Actor Ema Deepspeed   URL Share it on

  17   
  Autotrain compatible   Chatgpt   Dataset:dahoas/full-hh-rlhf Dataset:dahoas/synthetic-instr... Dataset:openai/webgpt comparis...   Dataset:stanfordnlp/shp Dataset:yitingxie/rlhf-reward-...   Deepspeed   En   Endpoints compatible   Instruct   Opt   Pytorch   Region:us   Rlhf   Sft
Model Card on HF 🤗: https://huggingface.co/AdamG012/chat-opt-1.3b-rlhf-actor-ema-deepspeed 

Chat Opt 1.3B Rlhf Actor Ema Deepspeed Benchmarks

LLME Score: 0.08276
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Chat Opt 1.3B Rlhf Actor Ema Deepspeed (AdamG012/chat-opt-1.3b-rlhf-actor-ema-deepspeed)
🌟 Advertise your project 🚀

Chat Opt 1.3B Rlhf Actor Ema Deepspeed Parameters and Internals

Model Type 
OPT, chat model
Additional Notes 
The model is optimized using an exponential moving average (EMA) method to enhance conversational response quality.
Training Details 
Data Sources:
Dahoas/full-hh-rlhf, Dahoas/synthetic-instruct-gptj-pairwise, yitingxie/rlhf-reward-datasets, openai/webgpt_comparisons, stanfordnlp/SHP
Methodology:
The model is trained through a three-step procedure involving supervised fine-tuning, reward model fine-tuning, and reinforcement learning from human feedback (RLHF) fine-tuning. This training process utilizes DeepSpeed for efficiency and scalability.
Context Length:
2048
Model Architecture:
FFN Dimensions: 8192, Hidden Size: 2048, Max Position Embedding: 2048, Attention Heads: 16, Hidden layers: 24
LLM NameChat Opt 1.3B Rlhf Actor Ema Deepspeed
Repository 🤗https://huggingface.co/AdamG012/chat-opt-1.3b-rlhf-actor-ema-deepspeed 
Model Size1.3b
Required VRAM2.6 GB
Updated2025-08-20
MaintainerAdamG012
Model Typeopt
Instruction-BasedYes
Model Files  2.6 GB
Supported Languagesen
Model ArchitectureOPTForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Vocabulary Size50272
Torch Data Typefloat16
Activation Functionrelu

Best Alternatives to Chat Opt 1.3B Rlhf Actor Ema Deepspeed

Best Alternatives
Context / RAM
Downloads
Likes
LongForm OPT 1.3B2K / 5.3 GB127
...speed Chat Step1 Model Opt1.3B2K / 2.6 GB152
...Opt 1.3B Rlhf Critic Deepspeed2K / 0.7 GB153
Chat Opt 1.3B Sft Deepspeed2K / 2.6 GB219
... Opt 1.3B Rlhf Actor Deepspeed2K / 3.2 GB175
Galactica 1.3B V22K / 2.6 GB173
Note: green Score (e.g. "73.2") means that the model is better than AdamG012/chat-opt-1.3b-rlhf-actor-ema-deepspeed.

Rank the Chat Opt 1.3B Rlhf Actor Ema Deepspeed Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 50767 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer