Model Card on HF 🤗: https://huggingface.co/mohitsha/opt-125m-quantized-brevitas
Opt 125M Quantized Brevitas 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)
Opt 125M Quantized Brevitas Parameters and Internals
| LLM Name | Opt 125M Quantized Brevitas |
| Repository 🤗 | https://huggingface.co/mohitsha/opt-125m-quantized-brevitas |
| Model Size | 125m |
| Updated | 2025-02-05 |
| Maintainer | mohitsha |
| Model Type | opt |
| Model Architecture | OPTForCausalLM |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.39.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 50272 |
| Activation Function | relu |
| Errors | replace |
Best Alternatives to Opt 125M Quantized Brevitas
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...125M Qcqa Ub 6 Best For Q Loss | 2K / 0.5 GB | 1209 | 0 |
| ...5M Qcqa Ub 6 Best For KV Cache | 2K / 0.5 GB | 1212 | 0 |
| ...25M Gqa Ub 6 Best For KV Cache | 2K / 0.5 GB | 1211 | 0 |
| Galactica 125M Cot | 2K / 0.5 GB | 149 | 0 |
| Galactica Ref | 2K / 0.5 GB | 143 | 0 |
| Opt 125M | 2K / 0.3 GB | 6286642 | 177 |
| Galactica 125M DPO Pos | 2K / 0.5 GB | 140 | 0 |
| Galactica 125M DPO | 2K / 0.5 GB | 140 | 0 |
| BertQA | 2K / 0.5 GB | 125 | 0 |
| BertQA | 2K / 0.5 GB | 141 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mohitsha/opt-125m-quantized-brevitas .
Rank the Opt 125M Quantized Brevitas 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227