| Additional Notes |
|
| LLM Name | InternLM2 Chat 20B ToxicRP |
| Repository ๐ค | https://huggingface.co/Aculi/InternLM2-Chat-20B-ToxicRP |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 20b |
| Required VRAM | 39.9 GB |
| Updated | 2025-09-27 |
| Maintainer | Aculi |
| Model Type | llama |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.1 |
| Is Biased | 0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 92544 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a Quality Float32 4 25bpw EXL2 | 4K / 10.9 GB | 5 | 2 |
| ...ra Quality Float32 8 0bpw EXL2 | 4K / 17.5 GB | 8 | 1 |
| ...ra Quality Float32 5 0bpw EXL2 | 4K / 12.8 GB | 5 | 0 |
| ... Unquirked 20B 4.25bpw H8 EXL2 | 4K / 11 GB | 5 | 1 |
| ...a No Robots 20B 3.0bpw H6 EXL2 | 4K / 7.8 GB | 5 | 1 |
| ...Cetacean 20B V2.4.0bpw H6 EXL2 | 4K / 10.3 GB | 8 | 1 |
| DaringMaid 20B V1.1 4bpw EXL2 | 4K / 10.4 GB | 6 | 2 |
| DaringMaid 20B V1.1 3bpw EXL2 | 4K / 7.9 GB | 5 | 1 |
| DaringMaid 20B 6bpw EXL2 | 4K / 15.3 GB | 7 | 2 |
| DaringMaid 20B 3bpw EXL2 | 4K / 7.9 GB | 7 | 1 |
๐ 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! ๐