LLM Name | Guanaco 33B SuperHOT 8K |
Repository ๐ค | https://huggingface.co/Panchovix/Guanaco-33B-SuperHOT-8k |
Merged Model | Yes |
Model Size | 33b |
Required VRAM | 65.2 GB |
Updated | 2024-09-16 |
Maintainer | Panchovix |
Model Type | llama |
Model Files | |
Context Length | 8k |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.30.2 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32000 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Guanaco 33B SuperHOT 8K Fp16 | 4 | 9 | 65 GB |
Guanaco 33B SuperHOT 8K GPTQ | 19 | 12 | 16 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Chronos Divergence 33B | 16K / 65 GB | 237 | 22 |
AutoCoder | 16K / 67 GB | 144 | 93 |
Deepseek Wizard 33B Slerp | 16K / 35.3 GB | 5 | 0 |
ValidateAI 33B Slerp | 16K / 35.4 GB | 6 | 0 |
Deepseek Coder 33B Instruct | 16K / 66.5 GB | 4715 | 444 |
OpenCodeInterpreter DS 33B | 16K / 66.5 GB | 1375 | 124 |
WhiteRabbitNeo 33B V1 | 16K / 67 GB | 687 | 80 |
ValidateAI 3 33B Ties | 16K / 66.5 GB | 5 | 0 |
ValidateAI 2 33B AT | 16K / 66.5 GB | 5 | 0 |
ReflectionCoder DS 33B | 16K / 67 GB | 159 | 4 |
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