4-bit Adapter Alignment-handbook Base model:adapter:google/gemm... Base model:google/gemma-7b Bitsandbytes Dataset:chansung/synth ds Finetuned Gemma Generated from trainer Lora Peft Region:us Safetensors Sft Tensorboard Trl
Llamaduo Synth Ds V0.1 Benchmarks
ARC: 55.29 vs 96.7 (so35)-42.8%
HellaSwag: 76.67 vs 95.3 (gpt4)-19.5%
MMLU: 58.11 vs 88.3 (so35)-34.2%
TruthfulQA: 43.5 vs 59 (gpt4)-26.3%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 32.6 vs 96.4 (so35)-66.2%
LLME Score: 0.23762
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)
Llamaduo Synth Ds V0.1 Parameters and Internals
| LLM Name | Llamaduo Synth Ds V0.1 |
| Repository 🤗 | https://huggingface.co/chansung/llamaduo_synth_ds_v0.1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.2 GB |
| Updated | 2024-09-16 |
| Maintainer | chansung |
| Model Files | |
| Model Architecture | Adapter |
| License | gemma |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|k_proj|up_proj|gate_proj|down_proj|q_proj|o_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Best Alternatives to Llamaduo Synth Ds V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeAstra 7B | 0K / 0 GB | 378 | 7 |
| ...Sql Flash Attention 2 Dataeval | 0K / 1.9 GB | 318 | 2 |
| Qwen1.5 7B Chat Sa V0.1 | 0K / 0 GB | 51 | 0 |
| Deepseek Llm 7B Chat Sa V0.1 | 0K / 0 GB | 5 | 0 |
| ...eze Embed Tokens Q V Proj Lora | 0K / 0.1 GB | 1 | 1 |
| Storytell | 0K / 0 GB | 6 | 0 |
| Zephyr 7B Gpo V5 I1 | 0K / 0.7 GB | 6 | 0 |
| Lora Adapted Mistral 7B | 0K / 0 GB | 50 | 0 |
| Zephyr 7B Gpo V6 I1 | 0K / 0.7 GB | 5 | 0 |
| Qwen Qwen1.5 7B 1719894406 | 0K / 0 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than chansung/llamaduo_synth_ds_v0.1 .
Rank the Llamaduo Synth Ds V0.1 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803