Arxiv:1910.09700 4-bit 4bit Autotrain compatible Conversational Endpoints compatible Gemma Gptq Quantized Region:us
SeaLLM 7B V2.5 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)
SeaLLM 7B V2.5 4bit Parameters and Internals
| LLM Name | SeaLLM 7B V2.5 4bit |
| Repository 🤗 | https://huggingface.co/venera-ai/SeaLLM-7B-v2.5-4bit |
| Model Size | 7b |
| Required VRAM | 7.2 GB |
| Updated | 2024-11-21 |
| Maintainer | venera-ai |
| Model Type | gemma |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | GemmaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to SeaLLM 7B V2.5 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Codegemma 7B It GPTQ | 8K / 7.2 GB | 1 | 1 |
| Gemma 1.1 7B It GPTQ | 8K / 7.2 GB | 9 | 1 |
| Google Gemma 7B 4 Bit Gptq | 8K / 5.6 GB | 16 | 1 |
| Google Gemma 7B 8 Bit Gptq | 8K / 9.5 GB | 16 | 0 |
| Gemma 7B Instruct GPTQ 4bit | 8K / 5.6 GB | 6 | 0 |
| CodeGemma 7B GPTQ | 8K / 7.2 GB | 36 | 0 |
| Codegemma 1.1 7B It GPTQ | 8K / 7.2 GB | 15 | 1 |
| Gemma 7B GPTQ | 8K / 7.2 GB | 266 | 0 |
| Gemma 7B It GPTQ | 8K / 7.2 GB | 8 | 0 |
| ...t Cleaner Gemma 32k Merged 16b | 31K / 17.1 GB | 18 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than venera-ai/SeaLLM-7B-v2.5-4bit .
Rank the SeaLLM 7B V2.5 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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110