Model Type |
| |||||
Additional Notes | Note: using quantized KV cache with Qwen2.5 is not recommended and can lead to degraded output quality. Using f16 should be okay. | |||||
Training Details |
| |||||
Input Output |
| |||||
Release Notes |
|
LLM Name | EVA Qwen2.5 14B V0.1 |
Repository ๐ค | https://huggingface.co/EVA-UNIT-01/EVA-Qwen2.5-14B-v0.1 |
Base Model(s) | |
Model Size | 14b |
Required VRAM | 29.7 GB |
Updated | 2024-11-13 |
Maintainer | EVA-UNIT-01 |
Model Type | qwen2 |
Instruction-Based | Yes |
Model Files | |
Model Architecture | Qwen2ForCausalLM |
License | apache-2.0 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.45.1 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 152064 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Rombos LLM V2.6 Qwen 14B | 128K / 29.7 GB | 4289 | 42 |
EVA Qwen2.5 14B V0.2 | 128K / 29.7 GB | 69 | 6 |
Tsunami 1.0 14B Instruct | 128K / 29.7 GB | 152 | 0 |
EVA Qwen2.5 14B V0.0 | 128K / 29.7 GB | 52 | 13 |
Qwen2.5 14B Instruct | 32K / 29.6 GB | 130877 | 113 |
Qwen2.5 Coder 14B Instruct | 32K / 29.7 GB | 316 | 27 |
Qwen2.5 Gutenberg Doppel 14B | 32K / 29.7 GB | 12 | 6 |
Qwen2.5 14B Instruct | 32K / 29.7 GB | 3547 | 6 |
Openthaigpt1.5 14B Instruct | 32K / 29.7 GB | 1234 | 3 |
Lambda Qwen2.5 14B DPO Test | 32K / 29.7 GB | 2673 | 7 |
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