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
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
---|---|---|---|---|
...Hermes 2 Mixtral 8x7B DPO 4bit | 68.4 | 32K / 10.6 GB | 9 | 18 |
...ixtral 8x7B DPO 2.4bpw H6 EXL2 | 68.4 | 32K / 14.3 GB | 1 | 1 |
...ralRPChat ZLoss 3.0bpw H6 EXL2 | 68.4 | 32K / 17.8 GB | 2 | 1 |
... Mixtral 8x7B SFT 3bpw H6 EXL2 | 68.4 | 32K / 17.8 GB | 6 | 0 |
...ralRPChat ZLoss 3.5bpw H6 EXL2 | 68.4 | 32K / 20.7 GB | 2 | 4 |
...ixtral 8x7B SFT 3.5bpw H6 EXL2 | 68.4 | 32K / 20.7 GB | 7 | 1 |
...ixtral 8x7B DPO 3.5bpw H6 EXL2 | 68.4 | 32K / 20.7 GB | 1 | 1 |
... 8x7B DPO 3.7bpw H6 EXL2 Rpcal | 68.4 | 32K / 21.9 GB | 2 | 4 |
...hon Mixtral V1.3.75bpw H6 EXL2 | 68.4 | 32K / 22.2 GB | 3 | 3 |
...ixtral 8x7B DPO 4.0bpw H6 EXL2 | 68.4 | 32K / 23.6 GB | 7 | 0 |
LLM Name | Nous Hermes 2 Mixtral 8x7B SFT GGUF |
Repository | Open on ๐ค |
Model Name | Nous Hermes 2 Mixtral 8X7B SFT |
Model Creator | NousResearch |
Base Model(s) | |
Required VRAM | 17.3 GB |
Updated | 2024-07-07 |
Maintainer | second-state |
Model Type | mixtral |
Model Files | |
Supported Languages | en |
GGUF Quantization | Yes |
Quantization Type | gguf|q2|q4_k|q5_k |
Model Architecture | MixtralForCausalLM |
License | apache-2.0 |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.36.0.dev0 |
Vocabulary Size | 32002 |
Initializer Range | 0.02 |
Torch Data Type | bfloat16 |