Autotrain Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-4 Conversational Custom code Dataset:lightningrodlabs/phi-4... Endpoints compatible Peft Phi3 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/LightningRodLabs/Flashlight-v1.1
Flashlight V1.1 Benchmarks
MMLU Pro: 49.06
GPQA: 11.97
MUSR: 9
BBH: 55.43
IFEval: 67.21 vs 88 (so35)-23.6%
MATH Lvl 5: 53.25
LLME Score: 0.32748
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)
Flashlight V1.1 Parameters and Internals
| LLM Name | Flashlight V1.1 |
| Repository 🤗 | https://huggingface.co/LightningRodLabs/Flashlight-v1.1 |
| Base Model(s) | |
| Model Size | 14.7b |
| Required VRAM | 29.4 GB |
| Updated | 2025-08-17 |
| Maintainer | LightningRodLabs |
| Model Type | phi3 |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.48.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100352 |
| Torch Data Type | float16 |
Best Alternatives to Flashlight V1.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Reasoning Plus | 32K / 29.4 GB | 11652 | 318 |
| Phi 4 Reasoning | 32K / 29.4 GB | 8483 | 200 |
| Phi 4 Reasoning Plus | 32K / 29.4 GB | 1298 | 4 |
| Phi 4 | 16K / 29.4 GB | 658809 | 2131 |
| Microsoft Phi 4 | 16K / 29.4 GB | 1076 | 55 |
| Phi 4 RP V0 | 16K / 29.5 GB | 4 | 3 |
| Phi4 Abliterated | 16K / 29.4 GB | 4 | 12 |
| Phi 4 AbliteratedRP | 16K / 29.5 GB | 6 | 5 |
| Phi 4 Abliterated | 16K / 29.4 GB | 32 | 31 |
| DNA R1 | 16K / 29.4 GB | 7264 | 39 |
Note: green Score (e.g. "73.2") means that the model is better than LightningRodLabs/Flashlight-v1.1 .
Rank the Flashlight V1.1 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? 50723 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124