Autotrain compatible Base model:mistralai/mixtral-8... Conversational Dataset:argilla/ultrafeedback-... Dpo En Endpoints compatible Exl2 Instruct License:apache-2.0 Mixtral Moe Preference Quantized Region:us Rlaif Safetensors Sharded Tensorflow Ultrafeedback
Notux 8x7b V1.3.5bpw EXL2 Benchmarks
HF Avg Score: 63.7 vs 86.1 (GPT-4) -26%
ARC: 61.8-35.8%
HellaSwag: 73.6-22.8%
MMLU: 62.6-27.6%
TruthfulQA: 625.1%
WinoGrande: 79.7-8.9%
GSM8K: 43.7-52.5%
OpenCompass Avg: 56.8 vs 73.3 (GPT-4) -22.5%
Exam: 71.4-7.5%
Language: 35.5-42.7%
Knowledge: 58.8-20%
Understanding: 66.7-4.7%
Reasoning: 54.7-26.5%
nn.n% — How the model compares to the GPT-4.
Rank the Notux 8x7b V1.3.5bpw EXL2 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 Notux 8x7b V1.3.5bpw EXL2
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...8x22b Instruct Oh EXL2 2.25bpw | 65.3 | 64K / 40.1 GB | 4 | 1 |
| ...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 H6 EXL2 | 63.7 | 32K / 20.7 GB | 1 | 1 |
| ...es Mixtral 8x7B 6.0bpw H6 EXL2 | 63.7 | 32K / 35.3 GB | 1 | 1 |
| ...ixtral 8x7B Instruct V0.1 GGUF | 63.7 | 32K / 17.3 GB | 499 | 5 |
| ...M 2 8x22B Beige 2.4bpw H6 EXL2 | — | 64K / 42.7 GB | 6 | 0 |
| ...M 2 8x22B Beige 3.0bpw H6 EXL2 | — | 64K / 53.2 GB | 15 | 0 |
| ...M 2 8x22B Beige 4.0bpw H6 EXL2 | — | 64K / 70.8 GB | 86 | 0 |
| ...M 2 8x22B Beige 5.0bpw H6 EXL2 | — | 64K / 88.5 GB | 10 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than JackCloudman/notux-8x7b-v1-3.5bpw-exl2 .
Notux 8x7b V1.3.5bpw EXL2 Parameters and Internals
| LLM Name | Notux 8x7b V1.3.5bpw EXL2 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Required VRAM | 20.7 GB |
| Updated | 2024-07-01 |
| Maintainer | JackCloudman |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | exl2 |
| Model Architecture | MixtralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.0 |
| 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? 34238 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801