Wendigo 14B Alpha4 is an open-source language model by MisterRid. Features: 14b LLM, VRAM: 28.4GB, Context: 32K, License: cc-by-nc-4.0, HF Score: 60.3, LLM Explorer Score: 0.14, Arc: 59.3, HellaSwag: 79.7, MMLU: 59.9, TruthfulQA: 55, WinoGrande: 74.7, GSM8K: 33.
Arxiv:1910.09700 Autotrain compatible Endpoints compatible Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/MisterRid/wendigo-14b-alpha4
Wendigo 14B Alpha4 Benchmarks
ARC: 59.3 vs 96.7 (so35)-38.7%
HellaSwag: 79.65 vs 95.3 (gpt4)-16.4%
MMLU: 59.85 vs 88.3 (so35)-32.2%
TruthfulQA: 54.98 vs 59 (gpt4)-6.8%
WinoGrande: 74.74 vs 87.5 (gpt4)-14.6%
GSM8K: 32.98 vs 96.4 (so35)-65.8%
LLME Score: 0.14278
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)
Wendigo 14B Alpha4 Parameters and Internals
| LLM Name | Wendigo 14B Alpha4 |
| Repository 🤗 | https://huggingface.co/MisterRid/wendigo-14b-alpha4 |
| Model Size | 14b |
| Required VRAM | 28.4 GB |
| Updated | 2024-12-07 |
| Maintainer | MisterRid |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Wendigo 14B Alpha4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ral Nemo Instruct 14B Merge V1 | 1000K / 24.6 GB | 19 | 0 |
| ColdBrew 12B NemoMix Test0 | 128K / 24.5 GB | 6 | 0 |
| K2S3 14B V0.2 | 32K / 28.7 GB | 5 | 0 |
| Qwen1.5 14B Chat Mistral | 32K / 28.6 GB | 9 | 4 |
| Mistral 14B Merge Base | 32K / 28.4 GB | 705 | 2 |
| Synthetic Minstrel 14B | 32K / 27.6 GB | 5 | 3 |
| Wandering Minstrel 14B | 32K / 27.6 GB | 8 | 3 |
| Phi 3 Medium 4K Instruct | 4K / 28 GB | 809 | 28 |
| Barcenas 14B Phi 3 Medium ORPO | 4K / 28 GB | 7996 | 5 |
| SauerkrautLM Phi 3 Medium | 4K / 28 GB | 8043 | 9 |
Note: green Score (e.g. "73.2") means that the model is better than MisterRid/wendigo-14b-alpha4 .
Rank the Wendigo 14B Alpha4 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a