Model Type |
| |||
Input Output |
|
LLM Name | SOLAR 10.7B Instruct V1.0 Uncensored AWQ |
Repository ๐ค | https://huggingface.co/TheBloke/SOLAR-10.7B-Instruct-v1.0-uncensored-AWQ |
Model Name | Solar 10.7B Instruct V1.0 Uncensored |
Model Creator | Stepan Zuev |
Base Model(s) | |
Model Size | 10.7b |
Required VRAM | 6 GB |
Updated | 2024-12-22 |
Maintainer | TheBloke |
Model Type | solar |
Instruction-Based | Yes |
Model Files | |
AWQ Quantization | Yes |
Quantization Type | awq |
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 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
SOLAR 10.7B Instruct V1.0 AWQ | 4K / 6 GB | 196 | 5 |
....0 Uncensored 8.0bpw H8 EXL2 2 | 4K / 10.9 GB | 16 | 2 |
....0 Uncensored 5.0bpw H6 EXL2 2 | 4K / 6.9 GB | 14 | 0 |
....0 Uncensored 4.0bpw H6 EXL2 2 | 4K / 5.6 GB | 13 | 0 |
....0 Uncensored 6.0bpw H6 EXL2 2 | 4K / 8.2 GB | 13 | 0 |
....0 Uncensored 3.0bpw H6 EXL2 2 | 4K / 4.3 GB | 12 | 0 |
... 10.7B Instruct V1.0 128K EXL2 | 128K / 5.6 GB | 14 | 1 |
...10.7B Instruct V1.0 Uncensored | 4K / 21.4 GB | 81 | 30 |
Eclectus 1.1 Dedup | 4K / 21.4 GB | 4804 | 0 |
Eclectus1.1 | 4K / 21.4 GB | 4813 | 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