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
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
Nous Hermes 2 Yi 34B GGUF | 40 | 2022 | 14 GB |
Nous Hermes 2 Yi 34B AWQ | 7 | 87 | 19 GB |
Nous Hermes 2 Yi 34B GPTQ | 6 | 55 | 18 GB |
Nous Hermes 2 Yi 34B Marlin | 5 | 1 | 19 GB |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
UNA SimpleSmaug 34B V1beta | 77.41 | 32K / 69.2 GB | 2580 | 20 |
Smaug 34B V0.1 | 77.29 | 195K / 69.2 GB | 6598 | 57 |
Luminex 34B V0.2 | 77.19 | 32K / 68.9 GB | 1962 | 11 |
Luminex 34B V0.1 | 77.06 | 195K / 68.9 GB | 1279 | 8 |
Pearl 34B Ties | 75.48 | 195K / 67.8 GB | 1720 | 3 |
UNA 34BeagleSimpleMath 32K V1 | 75.45 | 32K / 69.2 GB | 1798 | 6 |
UNA 34Beagles 32K Bf16 V1 | 75.41 | 32K / 69.2 GB | 3261 | 9 |
Bagel Hermes 34B Slerp | 75.24 | 195K / 68.9 GB | 4652 | 1 |
HermesBagel 34B V0.1 | 75.15 | 4K / 68.9 GB | 1813 | 1 |
Yi 34B X2 | 75.02 | 195K / 68.9 GB | 1768 | 0 |
LLM Name | Nous Hermes 2 Yi 34B |
Repository | Open on ๐ค |
Base Model(s) | |
Merged Model | Yes |
Model Size | 34.4b |
Required VRAM | 69.2 GB |
Updated | 2024-06-17 |
Maintainer | NousResearch |
Model Type | llama |
Model Files | |
Supported Languages | en |
Model Architecture | LlamaForCausalLM |
License | apache-2.0 |
Context Length | 4096 |
Model Max Length | 4096 |
Transformers Version | 4.37.0.dev0 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 64000 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |