3bit Autotrain compatible Conversational Endpoints compatible Pytorch Quantized Quip Qwen2 Region:us Sharded
Qwen1.5 32B Chat Quip 3bit Parameters and Internals
| LLM Name | Qwen1.5 32B Chat Quip 3bit |
| Repository | Open on 🤗 |
| Model Size | 32b |
| Required VRAM | 14.8 GB |
| Updated | 2024-07-27 |
| Maintainer | Minami-su |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | 3bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen1.5 32B Chat Quip 3bit
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Qwen1.5 32B Chat 4bit | 0.2 | 32K / 54.9 GB | 11 | 3 |
| Qwen1.5 32B Chat 8bit | 0.2 | 32K / 54.9 GB | 9 | 1 |
| Deita 32B EXL2 8.0bpw | 0.2 | 32K / 33.2 GB | 6 | 1 |
| ...wen1.5 32B Chat 4.0bpw H6 EXL2 | 0.2 | 32K / 17.7 GB | 11 | 1 |
| Qwen1.5 32B 4bit | 0.2 | 32K / 19.5 GB | 14 | 1 |
| ...wen1.5 32B Chat 3.0bpw H6 EXL2 | 0.2 | 32K / 13.7 GB | 6 | 1 |
| Qwen1.5 32B Chat | 0.4 | 32K / 65.5 GB | 12532 | 104 |
| Qwen1.5 32B | 0.4 | 32K / 65.5 GB | 11318 | 77 |
| Qwen1.5 32B Chat GPTQ Int4 | 0.3 | 32K / 19.5 GB | 24604 | 27 |
| ...penbuddy Qwen1.5 32B V21.2 32K | 0.3 | 32K / 64.6 GB | 2055 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Minami-su/Qwen1.5-32B-Chat-quip-3bit .
Rank the Qwen1.5 32B Chat Quip 3bit 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501