4bit Autotrain compatible Baichuan Custom code Endpoints compatible Pytorch Quantized Region:us Sharded
Model Card on HF 🤗: https://huggingface.co/lmdeploy/baichuan2-chat-7b-4bit
Baichuan2 Chat 7B 4bit 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 Chat 7B 4bit Parameters and Internals
| Model Type |
|
| LLM Name | Baichuan2 Chat 7B 4bit |
| Repository 🤗 | https://huggingface.co/lmdeploy/baichuan2-chat-7b-4bit |
| Model Size | 7b |
| Required VRAM | 5.6 GB |
| Updated | 2025-08-20 |
| Maintainer | lmdeploy |
| Model Type | baichuan |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | BaichuanForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.33.3 |
| Tokenizer Class | BaichuanTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 125696 |
| Torch Data Type | float16 |
Best Alternatives to Baichuan2 Chat 7B 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Baichuan2 7B PoSE YaRN 16K | 16K / 15 GB | 7 | 1 |
| Baichuan2 7B PoSE NTK 16K | 16K / 15 GB | 7 | 1 |
| Baichuan2 7B PoSE Linear 16K | 16K / 15 GB | 6 | 1 |
| Baichuan2 7B Chat | 4K / 15 GB | 25132 | 166 |
| DocLLM Baichuan2 7b | 4K / 18.3 GB | 6 | 5 |
| Selfrag Zh Baichuan2 7b Chat | 4K / 15 GB | 3 | 5 |
| HuatuoGPT2 7B | 4K / 15 GB | 953 | 10 |
| Baichuan2 7B Base | 4K / 15 GB | 2349 | 84 |
| Blossom V4 Baichuan2 7B | 4K / 15 GB | 5 | 1 |
| HuatuoGPT2 7B 4bits | 4K / 5.4 GB | 19 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than lmdeploy/baichuan2-chat-7b-4bit .
Rank the Baichuan2 Chat 7B 4bit 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? 50767 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124