Model Card on HF 🤗: https://huggingface.co/WisdomShell/Shell-7B-Chat
Shell 7B Chat 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)
Shell 7B Chat Parameters and Internals
| LLM Name | Shell 7B Chat |
| Repository 🤗 | https://huggingface.co/WisdomShell/Shell-7B-Chat |
| Model Size | 7b |
| Required VRAM | 15.3 GB |
| Updated | 2025-06-17 |
| Maintainer | WisdomShell |
| Model Type | codeshell |
| Model Files | |
| Supported Languages | zh en |
| Model Architecture | CodeShellForCausalLM |
| Transformers Version | 4.36.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 70144 |
| Torch Data Type | bfloat16 |
| Activation Function | gelu_pytorch_tanh |
| Errors | replace |
Best Alternatives to Shell 7B Chat
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Shell 7B | 0K / 15.4 GB | 6 | 0 |
| CodeShell 7B | 0K / 15.4 GB | 324 | 81 |
| CodeShell 7B Chat | 0K / 15.4 GB | 24 | 26 |
Rank the Shell 7B Chat 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? 48186 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124