4-bit Autotrain compatible Base model:nanbeige/nanbeige-1... Base model:quantized:nanbeige/... Custom code En Gptq Nanbeige Quantized Region:us Safetensors Sharded Tensorflow Zh
Nanbeige 16B Chat GPTQ 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)
Nanbeige 16B Chat GPTQ Parameters and Internals
| LLM Name | Nanbeige 16B Chat GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Nanbeige-16B-Chat-GPTQ |
| Model Name | Nanbeige 16B Chat |
| Model Creator | Nanbeige LLM Lab |
| Base Model(s) | |
| Model Size | 16b |
| Required VRAM | 9.2 GB |
| Updated | 2024-09-07 |
| Maintainer | TheBloke |
| Model Type | nanbeige |
| Model Files | |
| Supported Languages | en zh |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | NanbeigeForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | NanbeigeTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 59136 |
| Torch Data Type | bfloat16 |
Best Alternatives to Nanbeige 16B Chat GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Nanbeige 16B Base GPTQ | 4K / 9.2 GB | 15 | 2 |
| Nanbeige 16B Chat 32K GPTQ | 4K / 9.2 GB | 17 | 3 |
| Nanbeige 16B Base 32K GPTQ | 4K / 9.2 GB | 14 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nanbeige-16B-Chat-GPTQ .
Rank the Nanbeige 16B Chat GPTQ 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803