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 |
---|---|---|---|
FusionNet 34Bx2 MoE GGUF | 5 | 273 | 22 GB |
FusionNet 34Bx2 MoE AWQ | 5 | 26 | 32 GB |
FusionNet 34Bx2 MoE GPTQ | 2 | 8 | 31 GB |
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
FusionNet 34Bx2 MoE V0.1 | — | 195K / 121.2 GB | 759 | 7 |
Yi 34Bx2 MoE 60B DPO | — | 195K / 121.8 GB | 2942 | 2 |
...34Bx2 MoE V0.1 Full Linear DPO | — | 195K / 121.8 GB | 757 | 2 |
... Cloudyu Mixtral 34Bx2 MoE 60B | — | 195K / 121.8 GB | 732 | 0 |
Mixtral 34Bx2 MoE 60B | — | 195K / 121.9 GB | 2575 | 111 |
Yi 34Bx2 MoE 60B | — | 195K / 121.9 GB | 1920 | 64 |
Bagel Hermes 2x34B | — | 195K / 121.9 GB | 736 | 15 |
Yi 34Bx2 MoE 200K | — | 195K / 121.9 GB | 1742 | 2 |
...DPO TomGrc FusionNet 34Bx2 MoE | — | 32K / 121.8 GB | 719 | 4 |
Nous Hermes 2 SUS Chat 2x34B | — | 4K / 121.9 GB | 1368 | 3 |
LLM Name | FusionNet 34Bx2 MoE |
Repository | Open on ๐ค |
Model Size | 60.8b |
Required VRAM | 121.2 GB |
Updated | 2024-07-04 |
Maintainer | TomGrc |
Model Type | mixtral |
Model Files | |
Supported Languages | en |
Model Architecture | MixtralForCausalLM |
License | mit |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <s> |
Vocabulary Size | 64000 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |