8-bit Autotrain compatible Base model:mistralai/mixtral-8... License:apache-2.0 Mixtral Moe Pretrained Region:us Safetensors Sharded Tensorflow
Rank the Mixtral 8x7B V0.1 Fp8 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! 🌟
Best Alternatives to Mixtral 8x7B V0.1 Fp8
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Mixtral 8x7B V0.1 | 77.95 | 32K / 93.6 GB | 1046472 | 1587 |
| Mixtral 8x7B Instruct V0.1 | 77.75 | 32K / 93.6 GB | 529186 | 3945 |
| ...lQA Mixtral 8x7B Instruct V0.1 | — | 32K / 43.3 GB | 5 | 2 |
| Mixtral 8x7B Instruct V0.1 FP8 | — | 32K / 47.1 GB | 237 | 1 |
| ...tral 8x7B Instruct V0.1 FP8 V3 | — | 32K / 47.1 GB | 36 | 0 |
| ...tral 8x7B Instruct V0.1 FP8 V2 | — | 32K / 47.1 GB | 11 | 0 |
| ...tral 8x7B Instruct V0.1 FP8 V1 | — | 32K / 47.1 GB | 6 | 0 |
| Aldan Mix 8x7B | — | 32K / 89.4 GB | 1 | 1 |
| Taiwan LLM 8x7B DPO | — | 32K / 90 GB | 574 | 18 |
| Mixtral Instruct ITR 8x7B | — | 32K / 91.4 GB | 1 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than FriendliAI/Mixtral-8x7B-v0.1-fp8 .
Mixtral 8x7B V0.1 Fp8 Parameters and Internals
| LLM Name | Mixtral 8x7B V0.1 Fp8 |
| Repository | Open on 🤗 |
| Model Name | mistralai/Mixtral-8x7B-v0.1 |
| Base Model(s) | |
| Model Size | 46.7b |
| Required VRAM | 47 GB |
| Updated | 2024-07-07 |
| Maintainer | FriendliAI |
| Model Type | mixtral |
| Model Files | |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
What open-source LLMs or SLMs are you in search of? 34531 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801