4-bit Adapter Adapter-transformers Base model:adapter:technocultu... Base model:technoculture/mt7bi... Bitsandbytes Dataset:argilla/distilabel-cap... Dataset:argilla/distilabel-int... Dataset:argilla/distilabel-mat... Dataset:jondurbin/truthy-dpo-v... En Finetuned Llama Lora Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Technoculture/MedMerge-6-7b-alpha-dpo
MedMerge 6 7B Alpha DPO Benchmarks
ARC: 54.27 vs 96.7 (so35)-43.9%
HellaSwag: 75.6 vs 95.3 (gpt4)-20.7%
MMLU: 52.65 vs 88.3 (so35)-40.4%
TruthfulQA: 43.94 vs 59 (gpt4)-25.5%
WinoGrande: 71.03 vs 87.5 (gpt4)-18.8%
GSM8K: 26.16 vs 96.4 (so35)-72.9%
LLME Score: 0.16187
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)
MedMerge 6 7B Alpha DPO Parameters and Internals
| Supported Languages |
| ||||||||||||
| Training Details |
|
| LLM Name | MedMerge 6 7B Alpha DPO |
| Repository 🤗 | https://huggingface.co/Technoculture/MedMerge-6-7b-alpha-dpo |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.6 GB |
| Updated | 2025-09-18 |
| Maintainer | Technoculture |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | mit |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <PAD> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|gate_proj|q_proj|down_proj|k_proj|up_proj|o_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
Best Alternatives to MedMerge 6 7B Alpha DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Megumin | 0K / 0.1 GB | 4 | 1 |
| Uk Fraud Chatbot Llama2 | 0K / 0.4 GB | 5 | 0 |
| ...s 25 Mistral 7B Irca DPO Pairs | 0K / 0.1 GB | 5 | 0 |
| Qwen1.5 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Zephyr 7B Ipo 0K 15K I1 | 0K / 0.7 GB | 7 | 0 |
| Hr Other 7B Lora | 0K / 0.2 GB | 30 | 0 |
| Deepseek Llm 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Deepthink Reasoning Adapter | 0K / 0.2 GB | 3 | 3 |
| ... Days Of Sodom LoRA Mistral 7B | 0K / 0.2 GB | 5 | 0 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Technoculture/MedMerge-6-7b-alpha-dpo .
Rank the MedMerge 6 7B Alpha DPO 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? 51415 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124