| Additional Notes |
|
| LLM Name | 19B TRUTH DPO |
| Repository ๐ค | https://huggingface.co/cloudyu/19B_TRUTH_DPO |
| Model Size | 19b |
| Required VRAM | 38.4 GB |
| Updated | 2025-09-23 |
| Maintainer | cloudyu |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...l 11Bx2 MoE 19B 3.0bpw H6 EXL2 | 4K / 7.5 GB | 9 | 3 |
| ...l 11Bx2 MoE 19B 8.0bpw H8 EXL2 | 4K / 19.4 GB | 5 | 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