Model Card on HF 🤗: https://huggingface.co/Quazim0t0/Loke-14B-sce
Loke 14B Sce Benchmarks
MMLU Pro: 48.9
GPQA: 15.32
MUSR: 17.56
BBH: 55.83
IFEval: 68.48 vs 88 (so35)-22.2%
MATH Lvl 5: 39.05
LLME Score: 0.35808
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)
Loke 14B Sce Parameters and Internals
| LLM Name | Loke 14B Sce |
| Repository 🤗 | https://huggingface.co/Quazim0t0/Loke-14B-sce |
| Merged Model | Yes |
| Model Size | 14b |
| Required VRAM | 29.5 GB |
| Updated | 2025-03-22 |
| Maintainer | Quazim0t0 |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|dummy_87|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Best Alternatives to Loke 14B Sce
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Qwen2.5llamaify 14B V23.1 200K | 195K / 29.7 GB | 1997 | 1 |
| ...Qwen2.5llamaify 14B V23.3 200K | 195K / 29.7 GB | 26 | 5 |
| GeM2 Llamion 14B LongChat | 195K / 29 GB | 3525 | 4 |
| Openbuddy Zero 14B V22.3 32K | 32K / 28 GB | 1636 | 1 |
| Phi Line 14B | 16K / 29.4 GB | 138 | 11 |
| Megatron Opus 14B 2.1 | 16K / 29.5 GB | 1525 | 4 |
| Rune 14B | 16K / 29.5 GB | 45 | 1 |
| Rosemary 14B | 16K / 29.5 GB | 57 | 0 |
| Sake 20B | 16K / 43.1 GB | 22 | 0 |
| Phi 4 ReasoningRP | 16K / 29.5 GB | 124 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Quazim0t0/Loke-14B-sce .
Rank the Loke 14B Sce 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? 45389 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227