Mistral 8x7b Chat Parameters and Internals
| LLM Name | Mistral 8x7b Chat |
| Repository | Open on 🤗 |
| Model Size | 7b |
| Required VRAM | 93.6 GB |
| Updated | 2024-07-27 |
| Maintainer | mattshumer |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32001 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mistral 8x7b Chat
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Multimaster 7B V6 | 0.3 | 32K / 142.5 GB | 2741 | 1 |
| Mixtral 7B 8expert | 0.3 | 32K / 93.6 GB | 12888 | 260 |
| MultiverseBuddy 15B MoE | 0.3 | 32K / 25.8 GB | 241 | 0 |
| Mini Mixtral V0.2 | 0.2 | 32K / 25.8 GB | 302 | 3 |
| Laserxtral | 0.2 | 32K / 48.3 GB | 935 | 78 |
| Lumina 2 | 0.2 | 32K / 37.1 GB | 239 | 0 |
| RogerWizard 12B MoE | 0.2 | 32K / 25.8 GB | 235 | 1 |
| StarlingMaths 12B MoE | 0.2 | 32K / 25.8 GB | 238 | 0 |
| MultiverseMath 12B MoE | 0.2 | 32K / 25.8 GB | 259 | 0 |
| WestLakeLaser 12B MoE | 0.2 | 32K / 25.8 GB | 245 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mattshumer/mistral-8x7b-chat .
Rank the Mistral 8x7b Chat Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501