Adapter Base model:adapter:kyujinpy/sa... Base model:kyujinpy/sakura-sol... Conversational Dataset:meta-math/metamathqa En Finetuned Instruct Llama Lora Metamathqa Peft Region:us Safetensors Sharded Solar Tensorflow
Model Card on HF 🤗: https://huggingface.co/Q-bert/MOLAR-10.7B
MOLAR 10.7B 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)
MOLAR 10.7B Parameters and Internals
| Model Type |
| |||||||||
| Supported Languages |
| |||||||||
| Training Details |
| |||||||||
| Input Output |
|
| LLM Name | MOLAR 10.7B |
| Repository 🤗 | https://huggingface.co/Q-bert/MOLAR-10.7B |
| Base Model(s) | |
| Model Size | 10.7b |
| Required VRAM | 21.4 GB |
| Updated | 2025-02-22 |
| Maintainer | Q-bert |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|gate_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to MOLAR 10.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Solar 10.7B V1.0 Adapter | 0K / 0.2 GB | 15 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Q-bert/MOLAR-10.7B .
Rank the MOLAR 10.7B 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