Mpt 125M C4 is an open-source language model by wtang06. Features: 125m LLM, VRAM: 0.3GB, License: apache-2.0, HF Score: 28.8, LLM Explorer Score: 0.16, Arc: 22.2, HellaSwag: 26.4, MMLU: 24.7, TruthfulQA: 49.1, WinoGrande: 50.7.
Model Card on HF 🤗: https://huggingface.co/wtang06/mpt-125m-c4
Mpt 125M C4 Benchmarks
ARC: 22.18 vs 96.7 (so35)-77.1%
HellaSwag: 26.41 vs 95.3 (gpt4)-72.3%
MMLU: 24.68 vs 88.3 (so35)-72%
TruthfulQA: 49.08 vs 59 (gpt4)-16.8%
WinoGrande: 50.67 vs 87.5 (gpt4)-42.1%
LLME Score: 0.16137
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 125M C4 Parameters and Internals
| Model Type |
| ||||||||||||
| Use Cases |
| ||||||||||||
| Supported Languages |
| ||||||||||||
| Training Details |
|
| LLM Name | Mpt 125M C4 |
| Repository 🤗 | https://huggingface.co/wtang06/mpt-125m-c4 |
| Model Size | 125m |
| Required VRAM | 0.3 GB |
| Updated | 2026-03-29 |
| Maintainer | wtang06 |
| Model Type | mpt |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MPTForCausalLM |
| License | apache-2.0 |
| Model Max Length | 2048 |
| Transformers Version | 4.33.1 |
| Tokenizer Class | GPTNeoXTokenizer |
| Vocabulary Size | 50368 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mpt 125M C4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Ipt 125M | 0K / 0.3 GB | 7 | 0 |
Rank the Mpt 125M C4 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? 52473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a