Arxiv:2010.04245 Arxiv:2108.12409 Arxiv:2205.14135 8-bit Autotrain compatible Codegen Composer Custom code Instruct Llm-foundry Mosaicml Mpt Q8 Quantized Region:us Safetensors Sharded Tensorflow
Mpt 30B Chat Q8 Benchmarks
LMSys ELO: 1046 vs 1272 (so35)-17.8%
ARC: 58.7 vs 96.7 (so35)-39.3%
HellaSwag: 82.54 vs 95.3 (gpt4)-13.4%
MMLU: 51.16 vs 88.3 (so35)-42.1%
TruthfulQA: 52.42 vs 59 (gpt4)-11.2%
WinoGrande: 75.3 vs 87.5 (gpt4)-13.9%
GSM8K: 12.13 vs 96.4 (so35)-87.4%
LLME Score: 0.2372
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Mpt 30B Chat Q8 Parameters and Internals
| LLM Name | Mpt 30B Chat Q8 |
| Repository 🤗 | https://huggingface.co/Abzu/mpt-30b-chat-q8 |
| Base Model(s) | |
| Model Size | 30b |
| Required VRAM | 30.4 GB |
| Updated | 2024-09-16 |
| Maintainer | Abzu |
| Model Type | mpt |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | q8 |
| Generates Code | Yes |
| Model Architecture | MPTForCausalLM |
| License | cc-by-nc-sa-4.0 |
| Model Max Length | 8192 |
| Transformers Version | 4.30.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mpt 30B Chat Q8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Ct2fast Mpt 30B Chat | 0K / 30 GB | 8 | 2 |
Rank the Mpt 30B Chat Q8 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! 🌟
What open-source LLMs or SLMs are you in search of? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803