4-bit Autotrain compatible Awq Conversational En Endpoints compatible Pretrained Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
CodeQwen1.5 7B AWQ Benchmarks
CodeQwen1.5 7B AWQ Parameters and Internals
| LLM Name | CodeQwen1.5 7B AWQ |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 5.3 GB |
| Updated | 2024-07-27 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <fim_pad> |
| Vocabulary Size | 92416 |
| Torch Data Type | float16 |
Best Alternatives to CodeQwen1.5 7B AWQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Samantha Qwen2 7B AWQ | 0.2 | 128K / 5.6 GB | 48 | 0 |
| Dolphin 2.9.2 Qwen2 7B AWQ | 0.2 | 128K / 5.6 GB | 67 | 0 |
| CodeQwen1.5 7B Chat AWQ | 0.3 | 64K / 5.3 GB | 3331 | 10 |
| Qwen2 7B Instruct AWQ | 0.3 | 32K / 5.6 GB | 3412 | 14 |
| Qwen1.5 7B Chat AWQ | 0.3 | 32K / 5.9 GB | 1583 | 12 |
| Qwen1.5 7B AWQ W4 G128 | 0.2 | 32K / 5.9 GB | 7 | 0 |
| Qwen2 7B Bnb 4bit | 0.3 | 128K / 5.5 GB | 5822 | 2 |
| Tantrum 16bit | 0.3 | 128K / 15.2 GB | 168 | 0 |
| Qwen2 7B Matter 0.1 Slim A | 0.2 | 128K / 15.2 GB | 13 | 2 |
| ...lphin 2.9.2 Qwen2 7B Bpw6 EXL2 | 0.2 | 128K / 6.4 GB | 20 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/CodeQwen1.5-7B-AWQ .
Rank the CodeQwen1.5 7B AWQ 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