8-bit Autotrain compatible Chat Conversational En Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Qwen1.5 14B Chat GPTQ Int8 Parameters and Internals
| LLM Name | Qwen1.5 14B Chat GPTQ Int8 |
| Repository | Open on 🤗 |
| Model Size | 14b |
| Required VRAM | 16.5 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 | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen1.5 14B Chat GPTQ Int8
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| VinaLlama2 14B GPTQ Int4 | 0.2 | 32K / 9.7 GB | 25 | 2 |
| Qwen1.5 14B Chat GPTQ Int4 | 0.2 | 32K / 9.9 GB | 1038 | 19 |
| Liberated Qwen1.5 14B 4bit | 0.2 | 32K / 9.7 GB | 19 | 1 |
| Qwen1.5 14B Chat 4bit | 0.2 | 32K / 9.1 GB | 11 | 1 |
| Qwen1.5 14B Chat 8bpw H8 EXL2 | 0.2 | 32K / 15 GB | 7 | 1 |
| Qwen1.5 14B Chat 5bpw EXL2 | 0.2 | 32K / 10.1 GB | 6 | 1 |
| Qwen1.5 14B Chat | 0.4 | 32K / 28.3 GB | 27514 | 106 |
| Qwen1.5 14B | 0.4 | 32K / 28.3 GB | 27153 | 36 |
| Liberated Qwen1.5 14B | 0.3 | 32K / 28.4 GB | 5809 | 18 |
| ...penbuddy Qwen1.5 14B V21.1 32K | 0.3 | 32K / 28.4 GB | 1963 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-14B-Chat-GPTQ-Int8 .
Rank the Qwen1.5 14B 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