LLM Name | Phi 3 Mini 4K Japanese Tokenizer |
Repository ๐ค | https://huggingface.co/Hoshikuzu/Phi-3-mini-4k-japanese-tokenizer |
Model Size | 3.9b |
Required VRAM | 7.9 GB |
Updated | 2024-07-04 |
Maintainer | Hoshikuzu |
Model Type | phi3 |
Model Files | |
Model Architecture | Phi3ForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.42.3 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 51898 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi Jp Test Model | 4K / 15.8 GB | 17 | 1 |
...hi 3 Medium 128K Instruct 8bit | 128K / 14.9 GB | 28 | 2 |
Phi 3 Medium 4K Instruct 8bit | 4K / 14.9 GB | 21 | 0 |
...edium 128K Instruct GPTQ 8 Bit | 128K / 14.6 GB | 56 | 0 |
...um 128K Instruct GPTQ 8 Bit C4 | 128K / 14.6 GB | 18 | 0 |
... Medium 4K Instruct 8 Bit Gptq | 4K / 14.6 GB | 17 | 2 |
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