4-bit Autotrain compatible Awq Base model:mistralai/mixtral-8... De En Es Fr It License:apache-2.0 Mixtral Moe Quantized Region:us Safetensors Sharded Tensorflow
Mixtral 8x7b V0.1 AWQ Benchmarks
HF Avg Score: 57.7 vs 86.1 (GPT-4) -33%
ARC: 56.6-41.2%
HellaSwag: 72-24.4%
MMLU: 61.7-28.7%
TruthfulQA: 45.7-22.5%
WinoGrande: 78.6-10.2%
GSM8K: 33.7-63.4%
OpenCompass Avg: 59.6 vs 73.3 (GPT-4) -18.7%
Exam: 72.7-5.8%
Language: 45.2-27.1%
Knowledge: 63.2-14%
Understanding: 68-2.9%
Reasoning: 55.9-24.9%
nn.n% — How the model compares to the GPT-4.
Rank the Mixtral 8x7b V0.1 AWQ 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 AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| UNAversal 8x7B V1beta AWQ | 64.7 | 32K / 24.7 GB | 7 | 2 |
| Open Gpt4 8x7B V0.2 AWQ | 64.5 | 32K / 24.7 GB | 26 | 2 |
| ...ixtral Instruct 8x7b Zloss AWQ | 64.2 | 32K / 24.7 GB | 6 | 1 |
| ... Hermes 2 Mixtral 8x7B DPO AWQ | 64.1 | 32K / 24.7 GB | 437 | 20 |
| ...Hermes 2 Mixtral 8x7B DPO GPTQ | 64.1 | 32K / 24.7 GB | 1 | 1 |
| Notux 8x7b V1 AWQ | 64 | 32K / 24.7 GB | 7 | 3 |
| ...utLM Mixtral 8x7B Instruct AWQ | 63.8 | 32K / 24.7 GB | 417 | 2 |
| Mixtral 8x7B Instruct V0.1 AWQ | 63.7 | 32K / 24.7 GB | 1097 | 54 |
| Bagel DPO 8x7b V0.2 AWQ | 63.6 | 32K / 24.7 GB | 1 | 2 |
| ...Mixtral 8x7B V0.1 Dolly15K AWQ | 63.5 | 32K / 24.7 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/mixtral-8x7b-v0.1-AWQ .
Mixtral 8x7b V0.1 AWQ Parameters and Internals
| LLM Name | Mixtral 8x7b V0.1 AWQ |
| Repository | Open on 🤗 |
| Model Name | Mixtral 8X7B v0.1 |
| Model Creator | Mistral AI_ |
| Base Model(s) | |
| Model Size | 6.5b |
| Required VRAM | 24.7 GB |
| Updated | 2024-06-24 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Model Files | |
| Supported Languages | fr it de es en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | float16 |
What open-source LLMs or SLMs are you in search of? 34902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801