4-bit Autotrain compatible Awq Chat Conversational En Endpoints compatible Quantized Qwen2 Region:us Safetensors
Qwen1.5 4B Chat AWQ Benchmarks
ARC: 46.42 vs 96.7 (so35)-52%
HellaSwag: 69.1 vs 95.3 (gpt4)-27.5%
MMLU: 53.29 vs 88.3 (so35)-39.6%
TruthfulQA: 47.35 vs 59 (gpt4)-19.7%
WinoGrande: 63.3 vs 87.5 (gpt4)-27.7%
GSM8K: 4.7 vs 96.4 (so35)-95.1%
LLME Score: 0.24373
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 4B Chat AWQ Parameters and Internals
| LLM Name | Qwen1.5 4B Chat AWQ |
| Repository 🤗 | https://huggingface.co/Qwen/Qwen1.5-4B-Chat-AWQ |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 3.2 GB |
| Updated | 2024-09-07 |
| Maintainer | Qwen |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Qwen1.5 4B Chat AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen1.5 4B Chat | 32K / 7.9 GB | 20731 | 36 |
| Qwen1.5 4B | 32K / 7.9 GB | 12773 | 34 |
| Sailor 4B | 32K / 7.9 GB | 66 | 6 |
| Nusantara 4B Indo Chat | 32K / 7.9 GB | 96 | 1 |
| Sailor 4B Chat | 32K / 7.9 GB | 44 | 2 |
| Qwen 4B Flock 1719855002 | 32K / 7.9 GB | 5 | 0 |
| Qwen 4B Flock 1719848483 | 32K / 7.9 GB | 5 | 0 |
| NOVA 4B | 32K / 14.3 GB | 5 | 0 |
| Qwen 4B Flock 1719561695 | 32K / 7.9 GB | 5 | 0 |
| Qwen 4B Flock 1719564964 | 32K / 7.9 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-4B-Chat-AWQ .
Rank the Qwen1.5 4B Chat 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803