Ppo Hh Pythia 6B is an open-source language model by reciprocate. Features: 6b LLM, VRAM: 13.8GB, Context: 2K, LLM Explorer Score: 0.05.
Model Card on HF 🤗: https://huggingface.co/reciprocate/ppo_hh_pythia-6B
Ppo Hh Pythia 6B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Ppo Hh Pythia 6B Parameters and Internals
| LLM Name | Ppo Hh Pythia 6B |
| Repository 🤗 | https://huggingface.co/reciprocate/ppo_hh_pythia-6B |
| Model Size | 6b |
| Required VRAM | 13.8 GB |
| Updated | 2026-03-27 |
| Maintainer | reciprocate |
| Model Type | gpt_neox |
| Model Files | |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.25.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float16 |
Best Alternatives to Ppo Hh Pythia 6B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... GPT Neox 3 6B Instruction Ppo | 2K / 7.2 GB | 9 | 1 |
| 6B Sft Self Critiquing Refine | 2K / 27.5 GB | 6 | 0 |
| ...ia 6B Sft Response Full Static | 2K / 27.5 GB | 7 | 1 |
| Gptj Response Full Sft | 2K / 27.5 GB | 8 | 1 |
| Pythia 6B Static Sft | 2K / 27.5 GB | 8 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than reciprocate/ppo_hh_pythia-6B .
Rank the Ppo Hh Pythia 6B 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! 🌟
What open-source LLMs or SLMs are you in search of? 52394 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a