Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM-2B-dpo-int4
MiniCPM 2B DPO Int4 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)
MiniCPM 2B DPO Int4 Parameters and Internals
| LLM Name | MiniCPM 2B DPO Int4 |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM-2B-dpo-int4 |
| Model Size | 2b |
| Required VRAM | 2.5 GB |
| Updated | 2025-01-16 |
| Maintainer | openbmb |
| Model Files | |
| Model Architecture | MiniCPMForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 122753 |
| Torch Data Type | float16 |
Best Alternatives to MiniCPM 2B DPO Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM 2B 128K | 64K / 6 GB | 406 | 42 |
| MiniCPM 2B Sft Fp32 | 4K / 10.9 GB | 3917 | 295 |
| MiniCPM 2B Sft Bf16 | 4K / 5.5 GB | 7200 | 118 |
| ...iCPM 2B RAFT Lora Hotpotqa Dev | 4K / 5.5 GB | 31 | 0 |
| MiniCPM MoE 8x2B | 4K / 27.7 GB | 150 | 40 |
| MiniCPM Duplex | 4K / 5.5 GB | 18 | 2 |
| ...iniCPM 2B Sft Fp32 Safetensors | 4K / 10.9 GB | 7 | 1 |
| ...iniCPM 2B DPO Fp32 Safetensors | 4K / 10.9 GB | 7 | 1 |
| ...iniCPM 2B DPO Bf16 Safetensors | 4K / 5.5 GB | 2 | 1 |
| ...iniCPM 2B Sft Fp32 Safetensors | 4K / 10.9 GB | 2 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM-2B-dpo-int4 .
Rank the MiniCPM 2B DPO Int4 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? 41470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227