Arxiv:1910.09700 4-bit Autotrain compatible Conversational Endpoints compatible Gptq Lora Quantized Qwen2 Region:us Safetensors
Qwen2SFT GPTQ 4bits 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)
Qwen2SFT GPTQ 4bits Parameters and Internals
| LLM Name | Qwen2SFT GPTQ 4bits |
| Repository 🤗 | https://huggingface.co/SylvainShan/Qwen2SFT_GPTQ_4bits |
| Model Size | 0.5b |
| Required VRAM | 0.7 GB |
| Updated | 2024-09-07 |
| Maintainer | SylvainShan |
| Model Type | qwen2 |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen2SFT GPTQ 4bits
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 0.5B Instruct GPTQ Int4 | 32K / 0.7 GB | 903 | 12 |
| Qwen2 0.5B Instruct GPTQ Int8 | 32K / 1.5 GB | 292 | 2 |
| Qwen2Vanilla GPTQ 4bits | 32K / 0.7 GB | 6 | 0 |
| Qwen2SFT GPTQ 8bits | 32K / 0.9 GB | 5 | 0 |
| Qwen2Vanilla GPTQ 8bits | 32K / 0.9 GB | 5 | 0 |
| ...wen1.5 0.5B Chat SFT MCQA GPTQ | 32K / 0.8 GB | 5 | 0 |
| Qwen1.5 0.5B Chat GPTQ Int4 | 32K / 0.5 GB | 144 | 11 |
| Qwen1.5 0.5B Chat GPTQ Int8 | 32K / 0.6 GB | 73 | 2 |
| Qwen2 0.5B Bnb 4bit | 128K / 0.5 GB | 10928 | 2 |
| Ymail Search Qwen2 0.5B 16bit | 128K / 1 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than SylvainShan/Qwen2SFT_GPTQ_4bits .
Rank the Qwen2SFT GPTQ 4bits 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