Model Card on HF 🤗: https://huggingface.co/yfshi123/baichuan2-13b-chat-gptq-32g-act
Baichuan2 13B Chat Gptq 32g Act 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)
Baichuan2 13B Chat Gptq 32g Act Parameters and Internals
| LLM Name | Baichuan2 13B Chat Gptq 32g Act |
| Repository 🤗 | https://huggingface.co/yfshi123/baichuan2-13b-chat-gptq-32g-act |
| Model Size | 13b |
| Required VRAM | 9.9 GB |
| Updated | 2025-07-01 |
| Maintainer | yfshi123 |
| Model Type | baichuan |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | BaichuanForCausalLM |
| Model Max Length | 4096 |
| Transformers Version | 4.33.0 |
| Vocabulary Size | 125696 |
| Torch Data Type | float16 |
Best Alternatives to Baichuan2 13B Chat Gptq 32g Act
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sakura 13B LNovel V0.8 4bit | 0K / 9.1 GB | 58 | 2 |
| Sakura 13B LNovel V0.8 8bit | 0K / 9.1 GB | 42 | 1 |
| Sakura 13B LNovel V0.8 3bit | 0K / 7.5 GB | 34 | 1 |
| Baichuan2 13B Chat GPTQ | 0K / 9.1 GB | 40 | 21 |
| Baichuan2 13B Chat GPTQ Int4 | 0K / 9.1 GB | 28 | 2 |
| Baichuan 13B Instruction GPTQ | 0K / 7.9 GB | 18 | 4 |
| Baichuan 13B Chat 8bit | 0K / 14.1 GB | 23 | 9 |
| Tiny Random Baichuan2 13B | 0K / 0.1 GB | 97150 | 0 |
| Baichuan2 13B Chat | 0K / 27.8 GB | 7232 | 427 |
| Baichuan 13B Chat | 0K / 26.5 GB | 4801 | 631 |
Note: green Score (e.g. "73.2") means that the model is better than yfshi123/baichuan2-13b-chat-gptq-32g-act .
Rank the Baichuan2 13B Chat Gptq 32g Act 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? 49191 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124