Qwen1.5 7B Chat 4bit Benchmarks
ARC: 54.35 vs 96.7 (so35)-43.8%
HellaSwag: 76.8 vs 95.3 (gpt4)-19.4%
MMLU: 61.31 vs 88.3 (so35)-30.6%
TruthfulQA: 50.17 vs 59 (gpt4)-15%
WinoGrande: 69.77 vs 87.5 (gpt4)-20.3%
GSM8K: 19.86 vs 96.4 (so35)-79.4%
LLME Score: 0.21699
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 7B Chat 4bit Parameters and Internals
| LLM Name | Qwen1.5 7B Chat 4bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen1.5-7B-Chat-4bit |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 5.2 GB |
| Updated | 2024-10-18 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen1.5 7B Chat 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Bnb 4bit | 128K / 5.5 GB | 6212 | 1 |
| Qwen2 7B Bnb 4bit | 128K / 5.5 GB | 1912 | 3 |
| Tantrum 16bit | 128K / 15.2 GB | 15 | 0 |
| Qwen2 7B Matter 0.1 Slim A | 128K / 15.2 GB | 13 | 2 |
| ...lphin 2.9.2 Qwen2 7B Bpw6 EXL2 | 128K / 6.4 GB | 8 | 1 |
| PiSSA Qwen2 7B 4bit R128 5iter | 128K / 5.9 GB | 5 | 0 |
| Qwen2 7B Alpacha Merged 4bit | 128K / 5.6 GB | 6 | 0 |
| Qwen2 7B Alpacha Merged 16bit | 128K / 15.2 GB | 6 | 0 |
| Qwen2 7B 8bit | 128K / 8.1 GB | 9 | 1 |
| Qwen2 7B 4bit | 128K / 4.3 GB | 14 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen1.5-7B-Chat-4bit .
Rank the Qwen1.5 7B Chat 4bit 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803