8-bit Autotrain compatible Chat Conversational En Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Qwen1.5 4B Chat GPTQ Int8 Parameters and Internals
| LLM Name | Qwen1.5 4B Chat GPTQ Int8 |
| Repository | Open on 🤗 |
| Model Size | 4b |
| Required VRAM | 4.8 GB |
| Updated | 2024-07-27 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen1.5 4B Chat GPTQ Int8
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen1.5 4B Chat GPTQ Int4 | 0.2 | 32K / 3.2 GB | 235 | 4 |
| Qwen1.5 4B Chat | 0.3 | 32K / 7.9 GB | 15196 | 35 |
| Qwen1.5 4B | 0.3 | 32K / 7.9 GB | 31321 | 34 |
| Sailor 4B | 0.3 | 32K / 7.9 GB | 314 | 6 |
| Sailor 4B Chat | 0.3 | 32K / 7.9 GB | 373 | 2 |
| Nusantara 4B Indo Chat | 0.3 | 32K / 7.9 GB | 314 | 1 |
| Qwen1.5 4B Chat AWQ | 0.3 | 32K / 3.2 GB | 767 | 2 |
| Qwen1.5 Wukong 4B | 0.3 | 32K / 7.9 GB | 240 | 2 |
| Qwen 4B Flock 1719848483 | 0.3 | 32K / 7.9 GB | 26 | 0 |
| NOVA 3 1.5B | 0.3 | 32K / 14.3 GB | 34 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-4B-Chat-GPTQ-Int8 .
Rank the Qwen1.5 4B Chat GPTQ Int8 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501