| LLM Name | Phi 3 Vision 128K Instruct No Flash Attn |
| Repository ๐ค | https://huggingface.co/ggcristian/Phi-3-vision-128k-instruct-no-flash-attn |
| Model Size | 4.1b |
| Required VRAM | 8.3 GB |
| Updated | 2024-07-22 |
| Maintainer | ggcristian |
| Model Type | phi3_v |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3VForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3.5 Vision Instruct | 128K / 8.3 GB | 822840 | 704 |
| Phi 3 Vision 128K Instruct | 128K / 8.3 GB | 58648 | 965 |
| VLM2Vec Full | 128K / 8.3 GB | 91424 | 28 |
| Phi 3.5 Vision Instruct Bf16 | 128K / 8.3 GB | 61 | 2 |
| ...hi 3 HornyVision 128K Instruct | 128K / 8.3 GB | 8 | 28 |
| Phi 3 Vision 128K Instruct | 128K / 8.3 GB | 6 | 0 |
| Phi 3 Vision Win Snap | 128K / 8.3 GB | 6 | 1 |
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