LLM Name | Kiwi Solar Merge Ties2 DPO |
Repository ๐ค | https://huggingface.co/genne/kiwi_solar_merge_ties2_dpo |
Merged Model | Yes |
Model Size | 10.7b |
Required VRAM | 21.4 GB |
Updated | 2024-09-07 |
Maintainer | genne |
Model Type | llama |
Model Files | |
Supported Languages | ko |
Quantization Type | 32bit |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.35.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32000 |
LoRA Model | Yes |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
... 10.7B Instruct V1.0 128K EXL2 | 128K / 5.6 GB | 5 | 1 |
KoSoLAR 10.7B V0.2 1.4 Dedup 1 | 4K / 21.6 GB | 1967 | 0 |
KoSoLAR 10.7B V0.2 1.4 Dedup | 4K / 21.6 GB | 67 | 0 |
...e KoSoLAR 10.7B V0.2 1.4 Dedup | 4K / 43.2 GB | 68 | 0 |
Eclectus 1.1 Dedup | 4K / 21.4 GB | 1967 | 0 |
Eclectus1.1 | 4K / 21.4 GB | 1968 | 0 |
Solar 10.7B Bnb 4bit | 4K / 5.9 GB | 70 | 2 |
Frostwind 10.7B V1 EXL2 | 4K / 10.9 GB | 18 | 1 |
...ess 10.7B V1.5B 8.0bpw H8 EXL2 | 4K / 10.9 GB | 3 | 1 |
DaringLotus V2.10.7B 3bpw EXL2 | 4K / 4.3 GB | 3 | 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