LLM Name | DPO Model Test1 |
Repository ๐ค | https://huggingface.co/kimdeokgi/dpo_model_test1 |
Model Size | 21.4b |
Required VRAM | 43 GB |
Updated | 2024-10-16 |
Maintainer | kimdeokgi |
Model Type | llama |
Model Files | |
Supported Languages | en |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.37.2 |
Is Biased | 0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 92544 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Luxia 21.4B Alignment V1.2 | 32K / 43 GB | 6058 | 8 |
Luxia 21.4B Alignment V1.0 | 32K / 42.8 GB | 9421 | 32 |
UNA ThePitbull 21.4B V2 | 32K / 43 GB | 18 | 15 |
Final Model Test V2 | 32K / 43 GB | 7 | 0 |
UNA ThePitbull 21.4 V1 | 32K / 43 GB | 10 | 5 |
Sft Model Test1 | 32K / 43 GB | 17 | 0 |
Merge Model Test2 | 32K / 42.8 GB | 5 | 0 |
Merge Model Test1 | 32K / 42.8 GB | 6 | 0 |
Sft Model Test0 | 32K / 43 GB | 12 | 0 |
Alignment Model Test9 | 32K / 43 GB | 54 | 0 |
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