LLM Name | Swallow 70B Instruct Hf |
Repository ๐ค | https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf |
Model Size | 70b |
Required VRAM | 139.1 GB |
Updated | 2024-09-07 |
Maintainer | tokyotech-llm |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en ja |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.33.2 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 43176 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Swallow 70B Instruct GGUF | 8 | 153 | 29 GB |
Swallow 70B Instruct AWQ | 1 | 17 | 37 GB |
Swallow 70B Instruct GPTQ | 3 | 8 | 35 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
... 3 70B Instruct Gradient 1048K | 1024K / 141.9 GB | 1555 | 117 |
... Chat 1048K Chinese Llama3 70B | 1024K / 141.9 GB | 3164 | 5 |
Llama3 Function Calling 1048K | 1024K / 141.9 GB | 4 | 1 |
...a 3 70B Instruct Gradient 524K | 512K / 141.9 GB | 127 | 23 |
...a 3 70B Instruct Gradient 262K | 256K / 141.9 GB | 198 | 55 |
...ama 3 70B Arimas Story RP V2.0 | 256K / 141.1 GB | 106 | 3 |
...ama 3 70B Arimas Story RP V1.6 | 256K / 141.2 GB | 91 | 0 |
...ama 3 70B Arimas Story RP V1.5 | 256K / 141.2 GB | 113 | 2 |
Meta Llama 3.1 70B Instruct | 128K / 141.9 GB | 806015 | 444 |
...ma 3.1 70B Instruct Lorablated | 128K / 141.9 GB | 21965 | 49 |
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