Arxiv:2010.04245 Arxiv:2108.12409 Arxiv:2205.14135 8-bit Autotrain compatible Composer Custom code Dataset:anthropic/hh-rlhf Dataset:hello-simpleai/hc3 Dataset:jeffwan/sharegpt vicun... Dataset:tatsu-lab/alpaca Dataset:victor123/evol instruc... Instruct Llm-foundry Mosaicml Mpt Q8 Quantized Region:us Safetensors
Mpt 7B Chat Q8 Benchmarks
LMSys ELO: 928 vs 1272 (so35)-27%
ARC: 46.5 vs 96.7 (so35)-51.9%
HellaSwag: 75.51 vs 95.3 (gpt4)-20.8%
MMLU: 37.62 vs 88.3 (so35)-57.4%
TruthfulQA: 40.16 vs 59 (gpt4)-31.9%
WinoGrande: 68.43 vs 87.5 (gpt4)-21.8%
GSM8K: 4.09 vs 96.4 (so35)-95.8%
LLME Score: 0.20264
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 7B Chat Q8 Parameters and Internals
| LLM Name | Mpt 7B Chat Q8 |
| Repository 🤗 | https://huggingface.co/Abzu/mpt-7b-chat-q8 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 6.9 GB |
| Updated | 2024-09-18 |
| Maintainer | Abzu |
| Model Type | mpt |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | q8 |
| Model Architecture | MPTForCausalLM |
| License | cc-by-nc-sa-4.0 |
| Model Max Length | 2048 |
| Transformers Version | 4.30.2 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mpt 7B Chat Q8
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mpt 7B Instruct Q8 | 0K / 6.9 GB | 5 | 2 |
| Mpt 7B Chat | 0K / 13.3 GB | 3856 | 510 |
| Mpt 7B Instruct | 0K / 13.3 GB | 37815 | 461 |
| Sea Lion 7B Instruct | 0K / 15 GB | 3319 | 22 |
| Sea Lion 7B Instruct Gptq | 0K / 5.5 GB | 52 | 0 |
| Mpt 7B 8K Instruct | 0K / 13.3 GB | 820 | 25 |
| Sea Lion 7B Instruct Research | 0K / 15 GB | 42 | 14 |
| Mpt Instruct DotNet S | 0K / 4.6 GB | 700 | 1 |
| Mpt 7B 8K Chat Gptq | 0K / 3.8 GB | 5 | 2 |
| Results | 0K / 13.3 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Abzu/mpt-7b-chat-q8 .
Rank the Mpt 7B 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? 36026 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803