Arxiv:1910.09700 4-bit 4bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
PiSSA Qwen2 7B 4bit R128 5iter 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)
PiSSA Qwen2 7B 4bit R128 5iter Parameters and Internals
| LLM Name | PiSSA Qwen2 7B 4bit R128 5iter |
| Repository 🤗 | https://huggingface.co/fxmeng/PiSSA-Qwen2-7B-4bit-r128-5iter |
| Model Size | 7b |
| Required VRAM | 5.9 GB |
| Updated | 2024-09-07 |
| Maintainer | fxmeng |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.40.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to PiSSA Qwen2 7B 4bit R128 5iter
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 7B Bnb 4bit | 128K / 5.5 GB | 6079 | 2 |
| Tantrum 16bit | 128K / 15.2 GB | 7 | 0 |
| Qwen2 7B Matter 0.1 Slim A | 128K / 15.2 GB | 6 | 2 |
| Qwen2 7B 8bit | 128K / 8.1 GB | 54 | 1 |
| ...lphin 2.9.2 Qwen2 7B Bpw6 EXL2 | 128K / 6.4 GB | 10 | 1 |
| Qwen2 7B Alpacha Merged 4bit | 128K / 5.6 GB | 6 | 0 |
| Qwen2 7B Alpacha Merged 16bit | 128K / 15.2 GB | 6 | 0 |
| Qwen2 7B 4bit | 128K / 4.3 GB | 5 | 0 |
| CodeQwen1.5 7B EXL2 8.0bpw | 64K / 7.5 GB | 85 | 1 |
| ...odeQwen1.5 7B Chat EXL2 8.0bpw | 64K / 7.5 GB | 6 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than fxmeng/PiSSA-Qwen2-7B-4bit-r128-5iter .
Rank the PiSSA Qwen2 7B 4bit R128 5iter 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