4bit Base model:unsloth/gemma-7b-bn... En Endpoints compatible Gemma Gguf License:apache-2.0 Lora Quantized Region:us Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/ZEGMEG/CSD_QnA_Demo
CSD QnA Demo Parameters and Internals
| LLM Name | CSD QnA Demo |
| Repository 🤗 | https://huggingface.co/ZEGMEG/CSD_QnA_Demo |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.2 GB |
| Updated | 2024-07-04 |
| Maintainer | ZEGMEG |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | 4bit|gguf |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|gate_proj|up_proj|v_proj|o_proj|q_proj|k_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to CSD QnA Demo
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pixel | 8K / 4.4 GB | 17 | 0 |
| Mistral 7B Instruct V0.3 GGUF | 0K / 1.6 GB | 1458944 | 79 |
| Qwen2 7B Instruct GGUF | 0K / 1.9 GB | 1034279 | 11 |
| WizardLM 2 7B GGUF | 0K / 2.7 GB | 1321466 | 76 |
| Conversely Mistral 7B | 0K / 0.2 GB | 282 | 0 |
| Deepthink Reasoning 7B GGUF | 0K / 4.7 GB | 1341 | 11 |
| CleverBoi 7B V2 | 0K / 0.1 GB | 323 | 0 |
| Mistral 7B Instruct V0.3 GGUF | 0K / 2.7 GB | 70462 | 9 |
| Neumind Math 7B Instruct GGUF | 0K / 4.7 GB | 274 | 9 |
| QwQ LCoT 7B Instruct GGUF | 0K / 4.7 GB | 187 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than ZEGMEG/CSD_QnA_Demo .
Rank the CSD QnA Demo 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