LLM Name | Swallow 70B Instruct GPTQ |
Repository ๐ค | https://huggingface.co/TheBloke/Swallow-70B-instruct-GPTQ |
Model Name | Swallow 70B Instruct |
Model Creator | tokyotech-llm |
Base Model(s) | |
Model Size | 70b |
Required VRAM | 35.7 GB |
Updated | 2024-09-16 |
Maintainer | TheBloke |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Supported Languages | en ja |
GPTQ Quantization | Yes |
Quantization Type | gptq |
Model Architecture | LlamaForCausalLM |
License | llama2 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Beginning of Sentence Token | <s> |
End of Sentence Token | </s> |
Unk Token | <unk> |
Vocabulary Size | 43176 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...ama 3.1 70B Instruct Gptq 4bit | 128K / 39.9 GB | 321 | 4 |
Meta Llama 3 70B Instruct GPTQ | 8K / 39.8 GB | 1164 | 17 |
Meta Llama 3 70B Instruct GPTQ | 8K / 39.8 GB | 634 | 16 |
...a Llama 3 70B Instruct GPTQ 8B | 8K / 5 GB | 267 | 0 |
...ama 3 Taiwan 70B Instruct GPTQ | 8K / 39.8 GB | 19 | 2 |
...erkrautLM 70B Instruct GPTQ 8B | 8K / 5 GB | 157 | 1 |
...g Llama 3 70B Instruct GPTQ 8B | 8K / 5 GB | 3 | 1 |
...Llama 3 70B Instruct GPTQ Int4 | 8K / 39.8 GB | 104 | 6 |
...g Llama 3 70B Instruct GPTQ 4B | 8K / 9.9 GB | 5 | 0 |
...SauerkrautLM 70B Instruct GPTQ | 8K / 39.8 GB | 55 | 3 |
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