LLM Name | Oasst Rlhf 2 Llama 30B 7K Steps Hf |
Repository ๐ค | https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf |
Model Size | 30b |
Required VRAM | 65.2 GB |
Updated | 2024-09-20 |
Maintainer | Yhyu13 |
Model Type | llama |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 2048 |
Model Max Length | 2048 |
Transformers Version | 4.28.1 |
Tokenizer Class | LlamaTokenizer |
Vocabulary Size | 32006 |
Torch Data Type | float16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...2 Llama 30B 7K Steps Gptq 2bit | 2 | 6 | 9 GB |
...2 Llama 30B 7K Steps Gptq 4bit | 3 | 9 | 17 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Flash Llama 30M 20001 | 32K / 0.1 GB | 702 | 0 |
Smaug Slerp 30B V0.1 | 32K / 60.4 GB | 61 | 0 |
Llama33b 16K | 16K / 65.2 GB | 6 | 1 |
Yayi2 30B Llama | 4K / 121.2 GB | 719 | 22 |
... Tokens By Perplexity Bottom K | 4K / 5.4 GB | 6 | 0 |
... Tokens By Writing Style Top K | 4K / 5.4 GB | 16 | 0 |
...via Sample With Temperature2.0 | 4K / 5.4 GB | 9 | 0 |
...lue Sample With Temperature2.0 | 4K / 5.4 GB | 8 | 0 |
Yayi2 30B Guanaco | 4K / 60.6 GB | 4 | 2 |
Llama 30B Instruct 2048 | 2K / 65.2 GB | 4353 | 103 |
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