Merged Model Autotrain compatible Conversational En Endpoints compatible License:other Moe Pretrained Qwen2 Region:us Safetensors Sharded Tensorflow
Qwen1.5 32B Benchmarks
HF Avg Score: 70.39 vs 86.1 (GPT-4) -18.2%
ARC: 63.4-34.2%
HellaSwag: 85-10.8%
MMLU: 74.31-14.1%
TruthfulQA: 57.43-2.7%
WinoGrande: 81.29-7.1%
GSM8K: 60.88-33.8%
nn.n% — How the model compares to the GPT-4.
Rank the Qwen1.5 32B 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! 🌟
Best Alternatives to Qwen1.5 32B
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Deita 32B | 72.16 | 32K / 64.6 GB | 1345 | 1 |
| ...penbuddy Qwen1.5 32B V21.1 32K | 70.75 | 32K / 64.6 GB | 2155 | 3 |
| Matter 0.2 32B | 68.72 | 32K / 64.6 GB | 1383 | 2 |
| Einstein V4 Qwen 1.5 32B | 68.54 | 32K / 64.6 GB | 514 | 2 |
| SauerkrautLM Qwen 32B | 67.39 | 32K / 64.6 GB | 2410 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-32B .
Qwen1.5 32B Parameters and Internals
| LLM Name | Qwen1.5 32B |
| Repository | Open on 🤗 |
| Merged Model | Yes |
| Model Size | 32.5b |
| Required VRAM | 65.5 GB |
| Updated | 2024-06-24 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
| Errors | replace |
What open-source LLMs or SLMs are you in search of? 34902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801