Policy Iteration 1 is an open-source language model by AngelRaychev. Features: 134.5m LLM, VRAM: 0.5GB, Context: 8K, License: proprietary, LLM Explorer Score: 0.18.
| LLM Name | Policy Iteration 1 |
| Repository 🤗 | https://huggingface.co/AngelRaychev/policy_iteration_1 |
| Model Name | policy_iteration_1 |
| Base Model(s) | |
| Model Size | 134.5m |
| Required VRAM | 0.5 GB |
| Updated | 2025-05-24 |
| Maintainer | AngelRaychev |
| Model Type | llama |
| Model Files | |
| Gated Model | Yes |
| Model Architecture | LlamaForCausalLM |
| License | proprietary |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.51.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| BWork LLM | 8K / 0.3 GB | 6 | 0 |
| HyzeMini | 8K / 0.3 GB | 26 | 1 |
| Poker SmolLM | 8K / 0.5 GB | 1607 | 2 |
| SmolLM2 FT MyDataset | 8K / 0.5 GB | 5 | 0 |
| SmolLM2 FT MyDataset | 8K / 0.5 GB | 7 | 0 |
| Distilled Chat Ocra | 8K / 0.5 GB | 5 | 0 |
| SmolLM FT NYTCw | 2K / 0.5 GB | 6 | 0 |
| N1 | 2K / 0.5 GB | 23 | 1 |
| Value Iteration 1 | 2K / 0.5 GB | 12 | 0 |
| SmolLM FT CoEdIT | 2K / 0.5 GB | 6 | 0 |