Arxiv:1910.09700 Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-... Finetuned Lora Peft Region:us
Model Card on HF 🤗: https://huggingface.co/Vishal24/feature_mapping_adapter_v1
Feature Mapping Adapter V1 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)
Feature Mapping Adapter V1 Parameters and Internals
| LLM Name | Feature Mapping Adapter V1 |
| Repository 🤗 | https://huggingface.co/Vishal24/feature_mapping_adapter_v1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 1.2 GB |
| Updated | 2025-01-29 |
| Maintainer | Vishal24 |
| Model Files | |
| Model Architecture | Adapter |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | mlp.up_proj|self_attn.k_proj|self_attn.v_proj|lm_head.weight|input_layernorm.weight|self_attn.q_proj|post_attention_layernorm.weight|mlp.gate_proj|mlp.down_proj|model.norm.weight|self_attn.rotary_emb.inv_freq|self_attn.o_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Feature Mapping Adapter V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Megumin | 0K / 0.1 GB | 13 | 0 |
| ...s 25 Mistral 7B Irca DPO Pairs | 0K / 0.1 GB | 5 | 0 |
| Qwen1.5 7B Chat Sa V0.1 | 0K / 0 GB | 9 | 0 |
| Zephyr 7B Ipo 0K 15K I1 | 0K / 0.7 GB | 9 | 0 |
| Deepthink Reasoning Adapter | 0K / 0.2 GB | 27 | 8 |
| Deepseek Llm 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| ... Days Of Sodom LoRA Mistral 7B | 0K / 0.2 GB | 5 | 0 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 6 | 0 |
| CodeAstra 7B | 0K / 0 GB | 639 | 10 |
| ...eze Embed Tokens Q V Proj Lora | 0K / 0.1 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Vishal24/feature_mapping_adapter_v1 .
Rank the Feature Mapping Adapter V1 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