4-bit 4bit Autotrain compatible Bitsandbytes Conversational En Endpoints compatible Quantized Qwen2 Region:us Safetensors Unsloth
Qwen2 1.5B Bnb 4bit Benchmarks
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)
Qwen2 1.5B Bnb 4bit Parameters and Internals
| LLM Name | Qwen2 1.5B Bnb 4bit |
| Repository 🤗 | https://huggingface.co/unsloth/Qwen2-1.5B-bnb-4bit |
| Model Size | 1.5b |
| Required VRAM | 1.1 GB |
| Updated | 2024-09-08 |
| Maintainer | unsloth |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Qwen2 1.5B Bnb 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| IcaroLM | 128K / 3.1 GB | 125 | 1 |
| Qwen2 1.5B 4bit | 128K / 0.9 GB | 6 | 0 |
| Qwen2 1.5B Instruct Bnb 4bit | 32K / 1.1 GB | 18133 | 0 |
| Qwen2 1.5B It Chat | 32K / 3.1 GB | 269 | 0 |
| ...truct MoE CODE Assistant 16bit | 32K / 3.1 GB | 53 | 0 |
| ... 1.5B Instruct Replete Adapted | 32K / 3.1 GB | 992 | 2 |
| ...B Instruct MoE Assistant 16bit | 32K / 3.1 GB | 18 | 0 |
| Qwen2 1.5B Instruct MAC Lora | 32K / 1.2 GB | 5 | 0 |
| Jenna V3 Qwen2 1.5 | 32K / 3.1 GB | 6 | 0 |
| Jenna V3 Qwn2 1.5 4bit | 32K / 1.1 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2-1.5B-bnb-4bit .
Rank the Qwen2 1.5B Bnb 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803