4-bit Autotrain compatible Conversational Endpoints compatible Exl2 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Tess V2.5.2 Qwen2 72B 4 0bpw H6 EXL2 Pippa 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)
Tess V2.5.2 Qwen2 72B 4 0bpw H6 EXL2 Pippa Parameters and Internals
| LLM Name | Tess V2.5.2 Qwen2 72B 4 0bpw H6 EXL2 Pippa |
| Repository 🤗 | https://huggingface.co/denru/Tess-v2.5.2-Qwen2-72B-4_0bpw-h6-exl2-pippa |
| Model Size | 72b |
| Required VRAM | 38.6 GB |
| Updated | 2024-10-18 |
| Maintainer | denru |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Tess V2.5.2 Qwen2 72B 4 0bpw H6 EXL2 Pippa
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 72B Bnb 4bit | 128K / 41.2 GB | 97 | 3 |
| ...in 2.9.2 Qwen2 72B 6.0bpw EXL2 | 128K / 56.1 GB | 17 | 1 |
| Qwen2 72B 4bit | 128K / 40.9 GB | 57 | 0 |
| ...phin 292 Qwen2 72b EXL2 4 0bpw | 128K / 38.6 GB | 12 | 1 |
| ...n 2.9.2 Qwen72b 8.0bpw H8 EXL2 | 128K / 66.8 GB | 8 | 2 |
| ECE ILAB Q1 | 32K / 77.8 GB | 2147 | 0 |
| Qwen2.5 72B Instruct 4bit | 32K / 40.9 GB | 175 | 3 |
| Qwen2.5 72B Instruct 8bit | 32K / 77.1 GB | 50 | 2 |
| Qwen2 72B Instruct Bnb 4bit | 32K / 41.2 GB | 34 | 6 |
| Alpine Magnum 72B EXL2 5bpw | 32K / 47.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than denru/Tess-v2.5.2-Qwen2-72B-4_0bpw-h6-exl2-pippa .
Rank the Tess V2.5.2 Qwen2 72B 4 0bpw H6 EXL2 Pippa 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803