Phi3 Toxicity Judge Merge is an open-source language model by grounded-ai. Features: 3.8b LLM, VRAM: 15.4GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.13.
| Model Type |
| ||||||||||||
| Input Output |
|
| LLM Name | Phi3 Toxicity Judge Merge |
| Repository 🤗 | https://huggingface.co/grounded-ai/phi3-toxicity-judge-merge |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 15.4 GB |
| Updated | 2026-07-07 |
| Maintainer | grounded-ai |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float32 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Mini Instruct | 128K / 7.7 GB | 545512 | 785 |
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 688880 | 982 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 253628 | 1699 |
| Phi 4 Mini Instruct Heretic | 128K / 7.7 GB | 48 | 0 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 5 | 0 |
| MediPhi Instruct | 128K / 7.7 GB | 1671 | 69 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 6 | 0 |
| ECE EIFFEL 3Bv2 | 128K / 7.7 GB | 6 | 0 |
| Phi 4 Mini Instruct | 128K / 7.7 GB | 2492 | 24 |
🆘 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! 🌟