Autotrain compatible Conversational Endpoints compatible Ggml Gguf Pl Q8 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/piotr-ai/polanka-qwen2-3b-v0.1
Polanka Qwen2 3B V0.1 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)
Polanka Qwen2 3B V0.1 Parameters and Internals
| Supported Languages |
|
| LLM Name | Polanka Qwen2 3B V0.1 |
| Repository 🤗 | https://huggingface.co/piotr-ai/polanka-qwen2-3b-v0.1 |
| Model Size | 3b |
| Required VRAM | 6.9 GB |
| Updated | 2024-12-21 |
| Maintainer | piotr-ai |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | pl |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | ggml|q8|gguf |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Polanka Qwen2 3B V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...2.5 3B Instruct Abliterated V1 | 32K / 6.8 GB | 9 | 1 |
| QwQ LCoT 3B Instruct | 32K / 6.2 GB | 127 | 6 |
| Qwen2.5 3B Instruct Bnb 4bit | 32K / 2 GB | 8679 | 5 |
| Model92 | 32K / 6.8 GB | 14 | 0 |
| Thinik Orpo V2.0 | 32K / 6.2 GB | 11 | 0 |
| Saba1.5 Pro 3B | 128K / 5.8 GB | 56 | 1 |
| Qwen2.5 3B Instruct | 32K / 6.2 GB | 219480 | 116 |
| Qwen2.5 3B | 32K / 6.2 GB | 100806 | 43 |
| Calme 3.3 Instruct 3B | 32K / 11 GB | 8824 | 2 |
| Qwen2.5 Coder 3B Instruct | 32K / 6.2 GB | 68924 | 22 |
Note: green Score (e.g. "73.2") means that the model is better than piotr-ai/polanka-qwen2-3b-v0.1 .
Rank the Polanka Qwen2 3B V0.1 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? 40013 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217