4bit Autotrain compatible Chat Conversational En Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors
Qwen1.5 72B Chat GPTQ Benchmarks
ARC: 68.52 vs 96.7 (so35)-29.1%
HellaSwag: 86.42 vs 95.3 (gpt4)-9.3%
MMLU: 77.44 vs 88.3 (so35)-12.3%
TruthfulQA: 63.9 vs 59 (gpt4)8.3%
WinoGrande: 79.08 vs 87.5 (gpt4)-9.6%
GSM8K: 20.39 vs 96.4 (so35)-78.8%
LLME Score: 0.20827
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)
Qwen1.5 72B Chat GPTQ Parameters and Internals
| LLM Name | Qwen1.5 72B Chat GPTQ |
| Repository 🤗 | https://huggingface.co/LoneStriker/Qwen1.5-72B-Chat-GPTQ |
| Base Model(s) | |
| Model Size | 72b |
| Required VRAM | 45.4 GB |
| Updated | 2024-09-07 |
| Maintainer | LoneStriker |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen1.5 72B Chat GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2 72B Instruct GPTQ Int4 | 32K / 41.6 GB | 10182 | 29 |
| Qwen2 72B Instruct GPTQ Int8 | 32K / 77 GB | 6351 | 13 |
| Qwen1.5 72B Chat GPTQ Int4 | 32K / 41.3 GB | 4427 | 36 |
| Qwen1.5 72B Chat GPTQ Int8 | 32K / 77 GB | 57 | 6 |
| Qwen2 72B Bnb 4bit | 128K / 41.2 GB | 363 | 3 |
| ...in 2.9.2 Qwen2 72B 6.0bpw EXL2 | 128K / 56.1 GB | 5 | 1 |
| ...Qwen2 72B 4 0bpw H6 EXL2 Pippa | 128K / 38.6 GB | 6 | 1 |
| ...n 2.9.2 Qwen72b 8.0bpw H8 EXL2 | 128K / 66.8 GB | 5 | 2 |
| ...phin 292 Qwen2 72b EXL2 4 0bpw | 128K / 38.6 GB | 3 | 1 |
| Qwen2 72B 4bit | 128K / 40.9 GB | 8 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Qwen1.5-72B-Chat-GPTQ .
Rank the Qwen1.5 72B Chat GPTQ 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