Huginn V5.10.7B is an open-source language model by The-Face-Of-Goonery. Features: 11b LLM, VRAM: 21.4GB, Context: 32K, License: cc-by-4.0, Quantized, HF Score: 55.6, LLM Explorer Score: 0.27, Arc: 63.3, HellaSwag: 78.8, MMLU: 54.2, TruthfulQA: 44.5, WinoGrande: 73.7, GSM8K: 19.2.
Arxiv:2203.05482 Autotrain compatible Conversational Endpoints compatible Gguf License:cc-by-4.0 Merge Mergekit Mistral Q4 Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/The-Face-Of-Goonery/Huginn-V5-10.7B
Huginn V5.10.7B Benchmarks
ARC: 63.31 vs 96.7 (so35)-34.5%
HellaSwag: 78.8 vs 95.3 (gpt4)-17.3%
MMLU: 54.22 vs 88.3 (so35)-38.6%
TruthfulQA: 44.52 vs 59 (gpt4)-24.5%
WinoGrande: 73.72 vs 87.5 (gpt4)-15.7%
GSM8K: 19.18 vs 96.4 (so35)-80.1%
LLME Score: 0.27417
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)
Huginn V5.10.7B Parameters and Internals
| LLM Name | Huginn V5.10.7B |
| Repository 🤗 | https://huggingface.co/The-Face-Of-Goonery/Huginn-V5-10.7B |
| Model Size | 11b |
| Required VRAM | 21.4 GB |
| Updated | 2024-07-04 |
| Maintainer | The-Face-Of-Goonery |
| Model Type | mistral |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k |
| Model Architecture | MistralForCausalLM |
| License | cc-by-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Huginn V5.10.7B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Normistral 11B Warm | 1000K / 22.9 GB | 4329 | 11 |
| ... 11B V2.2 Instruct EXL2 4.5bit | 32K / 6.5 GB | 292 | 3 |
| ...B V2.2 Instruct HQQ 4bit 128gs | 32K / 6.2 GB | 30 | 3 |
| ...B V2.2 Instruct HQQ 8bit 128gs | 32K / 11.7 GB | 14 | 3 |
| ...t 3.1 Frankenmerge 11B Gguf Q8 | 32K / 8.3 GB | 17 | 1 |
| Bielik 11B V2.2 Instruct GPTQ | 32K / 6.2 GB | 223 | 3 |
| Bielik 11B V2.2 Instruct AWQ | 32K / 6.2 GB | 176 | 3 |
| Bielik 11B V2.2 Instruct FP8 | 32K / 11.4 GB | 101 | 3 |
| ... 11B V2.2 Instruct Quanto 8bit | 32K / 12 GB | 30 | 4 |
| Bielik 11B V2.2 Instruct W8A8 | 32K / 11.5 GB | 19 | 3 |
Rank the Huginn V5.10.7B 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? 53185 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