4-bit Autotrain compatible Chat Conversational En Endpoints compatible Gptq Instruct Quantized Qwen2 moe Region:us Safetensors Sharded Tensorflow
Qwen2 57B A14B Instruct GPTQ Int4 Parameters and Internals
| LLM Name | Qwen2 57B A14B Instruct GPTQ Int4 |
| Repository | Open on 🤗 |
| Model Size | 57b |
| Required VRAM | 31.6 GB |
| Updated | 2024-07-27 |
| Maintainer | Qwen |
| Model Type | qwen2_moe |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2MoeForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen2 57B A14B Instruct GPTQ Int4
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...7B A14B Instruct GPTQ Int4 MLX | 0.2 | 32K / 32.3 GB | 9 | 1 |
| Qwen2 57B A14B Instruct 8bit | 0.2 | 32K / 61.1 GB | 23 | 1 |
| Qwen2 57B A14B Instruct 4bit | 0.2 | 32K / 32.3 GB | 12 | 2 |
| Qwen2 57B A14B Instruct | 0.4 | 32K / 115.2 GB | 11385 | 62 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-57B-A14B-Instruct-GPTQ-Int4 .
Rank the Qwen2 57B A14B Instruct GPTQ Int4 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