Arxiv:1910.09700 Adapter Base model:adapter:unsloth/mis... Base model:unsloth/mistral-sma... Finetuned Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/trashpanda-org/MS-24B-Mullein-v1-lora
MS 24B Mullein V1 Lora 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)
MS 24B Mullein V1 Lora Parameters and Internals
| LLM Name | MS 24B Mullein V1 Lora |
| Repository 🤗 | https://huggingface.co/trashpanda-org/MS-24B-Mullein-v1-lora |
| Base Model(s) | |
| Model Size | 24b |
| Required VRAM | 0 GB |
| Updated | 2025-06-17 |
| Maintainer | trashpanda-org |
| Model Files | |
| Model Architecture | Adapter |
| Model Max Length | 32768 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|o_proj|gate_proj|down_proj|up_proj|k_proj|v_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0.25 |
| R Param | 128 |
Rank the MS 24B Mullein V1 Lora 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? 48225 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124