4-bit Autotrain compatible Base model:neversleep/noromaid... Conversational Gptq Instruct License:cc-by-nc-4.0 Mixtral Moe Quantized Region:us Safetensors
Noromaid V0.4 Mixtral Instruct 8x7b Zloss GPTQ Benchmarks
HF Avg Score: 64.2 vs 86.1 (GPT-4) -25.4%
ARC: 62-35.6%
HellaSwag: 73.9-22.5%
MMLU: 62.7-27.5%
TruthfulQA: 63.88.1%
WinoGrande: 80.1-8.5%
GSM8K: 44.3-51.8%
nn.n% — How the model compares to the GPT-4.
Rank the Noromaid V0.4 Mixtral Instruct 8x7b Zloss 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 Noromaid V0.4 Mixtral Instruct 8x7b Zloss GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...tLM Mixtral 8x7B Instruct GPTQ | 63.8 | 32K / 23.8 GB | 55 | 3 |
| ...ixtral 8x7B Instruct V0.1 GPTQ | 63.7 | 32K / 23.8 GB | 783803 | 127 |
| ...ixtral 8x7B V0.1 Dolly15K GPTQ | 63.5 | 32K / 23.8 GB | 7 | 2 |
| Dolphin 2.5 Mixtral 8x7b GPTQ | — | 32K / 23.8 GB | 216 | 89 |
| Dolphin 2.7 Mixtral 8x7b GPTQ | — | 32K / 23.8 GB | 431 | 18 |
| Dolphin 2.6 Mixtral 8x7b GPTQ | — | 32K / 23.8 GB | 11 | 6 |
| ....1 LimaRP ZLoss DARE TIES GPTQ | — | 32K / 23.8 GB | 7 | 6 |
| ...nstruct V0.1 LimaRP ZLoss GPTQ | — | 32K / 23.8 GB | 7 | 3 |
| ... Mixtral 8x7b Instruct V3 GPTQ | — | 32K / 23.8 GB | 12 | 2 |
Noromaid V0.4 Mixtral Instruct 8x7b Zloss GPTQ Parameters and Internals
| LLM Name | Noromaid V0.4 Mixtral Instruct 8x7b Zloss GPTQ |
| Repository | Open on 🤗 |
| Model Name | Noromaid V0.4 Mixtral Instruct 8X7B ZLoss |
| Model Creator | NeverSleep |
| Base Model(s) | |
| Model Size | 6.1b |
| Required VRAM | 23.8 GB |
| Updated | 2024-06-24 |
| Maintainer | TheBloke |
| Model Type | mixtral |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MixtralForCausalLM |
| License | cc-by-nc-4.0 |
| 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 | 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