LLM Name | Phi3 14B Unsloth Sft Gptq 3bit |
Repository ๐ค | https://huggingface.co/acl-srw-2024/phi3-14b-unsloth-sft-gptq-3bit |
Model Size | 14b |
Required VRAM | 6 GB |
Updated | 2025-02-16 |
Maintainer | acl-srw-2024 |
Model Type | mistral |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|3bit |
Model Architecture | MistralForCausalLM |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.41.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 32011 |
Torch Data Type | float16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Phi3 14B Unsloth Sft Gptq 8bit | 4K / 14.6 GB | 6 | 0 |
Arsh V1 | 4K / 28 GB | 939 | 1 |
...ll Phi 3 Medium 4K Inst Philos | 4K / 28 GB | 19 | 0 |
Phi 3 Unsloth Finetune 7 | 4K / 28 GB | 6 | 0 |
Phi 3 Unsloth Finetune 6 | 4K / 28 GB | 5 | 0 |
Phi 3 Unsloth Finetune 5 | 4K / 28 GB | 5 | 0 |
Phi 3 Unsloth Finetune 4 | 4K / 28 GB | 6 | 0 |
Phi 3 Unsloth Finetuned 3 | 4K / 28 GB | 6 | 0 |
...ral Nemo Instruct 14B Merge V1 | 1000K / 24.6 GB | 19 | 0 |
K2S3 14B V0.2 | 32K / 28.7 GB | 28 | 0 |
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