4-bit Adapter Axolotl Base model:adapter:carsonpoole... Base model:carsonpoole/qwen2-7... Bitsandbytes Finetuned Generated from trainer Instruct Lora Peft Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/carsonpoole/Qwen2-37B-Pruned
Qwen2 37B Pruned 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 37B Pruned Parameters and Internals
| LLM Name | Qwen2 37B Pruned |
| Repository 🤗 | https://huggingface.co/carsonpoole/Qwen2-37B-Pruned |
| Base Model(s) | |
| Model Size | 72b |
| Required VRAM | 0.8 GB |
| Updated | 2025-02-02 |
| Maintainer | carsonpoole |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|gate_proj|o_proj|up_proj|k_proj|down_proj|q_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
| Errors | replace |
Rank the Qwen2 37B Pruned 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227