Autotrain compatible Base model:mistralai/mixtral-8... En Gptq License:apache-2.0 Mixtral Moe Quantized Region:us Safetensors Vllm
Mixtral 8x7B V0.1 Int8 GPTQ 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 Int8 GPTQ 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 Int8 GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...8x22b Instruct Oh EXL2 2.25bpw | 65.3 | 64K / 40.1 GB | 2 | 1 |
| ...2 Mixtral 8x22b 6.0bpw H8 EXL2 | 65.3 | 64K / 105.8 GB | 0 | 1 |
| ...2 Mixtral 8x22b 8.0bpw H8 EXL2 | 65.3 | 64K / 125.1 GB | 6 | 2 |
| WizardLM2 2bit | 65.3 | 64K / 4.8 GB | 163 | 0 |
| ...Hermes 2 Mixtral 8x7B DPO GGUF | 64.1 | 32K / 17.3 GB | 451 | 2 |
| ...es Mixtral 8x7B 2.4bpw H6 EXL2 | 63.7 | 32K / 14.3 GB | 1 | 2 |
| ...es Mixtral 8x7B 3.0bpw H6 EXL2 | 63.7 | 32K / 17.8 GB | 1 | 1 |
| Notux 8x7b V1.3.5bpw EXL2 | 63.7 | 32K / 20.7 GB | 1 | 2 |
| Notux 8x7b V1.3.5bpw H6 EXL2 | 63.7 | 32K / 20.7 GB | 1 | 1 |
| ...es Mixtral 8x7B 6.0bpw H6 EXL2 | 63.7 | 32K / 35.3 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Inferless/Mixtral-8x7B-v0.1-int8-GPTQ .
Mixtral 8x7B V0.1 Int8 GPTQ Parameters and Internals
| LLM Name | Mixtral 8x7B V0.1 Int8 GPTQ |
| Repository | Open on 🤗 |
| Model Name | Mixtral-8x7B |
| Model Creator | mistralai |
| Base Model(s) | |
| Updated | 2024-06-24 |
| Maintainer | Inferless |
| Model Type | mixtral |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
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