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 |
---|---|---|---|
Nontoxic Bagel 34B V0.2 GGUF | 3 | 231 | 14 GB |
Nontoxic Bagel 34B V0.2 AWQ | 2 | 6 | 19 GB |
Nontoxic Bagel 34B V0.2 GPTQ | 1 | 6 | 18 GB |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
SUS Chat 34B | 85.03 | 8K / 68.9 GB | 1712 | 119 |
UNA SimpleSmaug 34B V1beta | 77.41 | 32K / 69.2 GB | 1626 | 20 |
Smaug 34B V0.1 | 77.29 | 195K / 69.2 GB | 3880 | 57 |
Luminex 34B V0.2 | 77.19 | 32K / 68.9 GB | 173 | 11 |
Luminex 34B V0.1 | 77.06 | 195K / 68.9 GB | 958 | 8 |
Pearl 34B Ties | 75.48 | 195K / 67.8 GB | 815 | 3 |
Bagel Hermes 34B Slerp | 75.24 | 195K / 68.9 GB | 3419 | 1 |
HermesBagel 34B V0.1 | 75.15 | 4K / 68.9 GB | 824 | 1 |
Yi 34B X2 | 75.02 | 195K / 68.9 GB | 813 | 0 |
Yi 1.5 34B Chat | 74.82 | 4K / 69.2 GB | 69571 | 188 |
LLM Name | Nontoxic Bagel 34B V0.2 |
Repository | Open on ๐ค |
Model Size | 34b |
Required VRAM | 68.7 GB |
Updated | 2024-07-01 |
Maintainer | jondurbin |
Model Type | llama |
Model Files | |
Model Architecture | LlamaForCausalLM |
License | other |
Context Length | 200000 |
Model Max Length | 200000 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 64000 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |