Model Card on HF 🤗: https://huggingface.co/abhinavkulkarni/mosaicml-mpt-30b-instruct-w4-g128-awq
Mosaicml Mpt 30B Instruct W4 G128 AWQ Benchmarks
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)
Mosaicml Mpt 30B Instruct W4 G128 AWQ Parameters and Internals
| Model Type |
|
| LLM Name | Mosaicml Mpt 30B Instruct W4 G128 AWQ |
| Repository 🤗 | https://huggingface.co/abhinavkulkarni/mosaicml-mpt-30b-instruct-w4-g128-awq |
| Model Size | 30b |
| Required VRAM | 16.1 GB |
| Updated | 2024-12-22 |
| Maintainer | abhinavkulkarni |
| Model Type | mpt |
| Instruction-Based | Yes |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MPTForCausalLM |
| License | cc-by-sa-3.0 |
| Model Max Length | 8192 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50432 |
| Torch Data Type | float16 |
Best Alternatives to Mosaicml Mpt 30B Instruct W4 G128 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mpt 30B Chat Q8 | 0K / 30.4 GB | 19 | 1 |
| Mpt 30B Instruct Q8 | 0K / 30.4 GB | 16 | 5 |
| Mpt 30B Instruct | 0K / 60.1 GB | 1263 | 101 |
| ...t 30B Instruct Peft Compatible | 0K / 60.1 GB | 13 | 2 |
| Ct2fast Mpt 30B Instruct | 0K / 30 GB | 9 | 4 |
| Ct2fast Mpt 30B Chat | 0K / 30 GB | 10 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than abhinavkulkarni/mosaicml-mpt-30b-instruct-w4-g128-awq .
Rank the Mosaicml Mpt 30B Instruct W4 G128 AWQ 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217