Autotrain compatible Conversational Endpoints compatible Gguf Mistral Q4 Quantized Region:us Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_Nous-Hermes-2-Mistral-7B-DPO
Candle Nous Hermes 2 Mistral 7B DPO Benchmarks
ARC: 66.04 vs 96.7 (so35)-31.7%
HellaSwag: 84.95 vs 95.3 (gpt4)-10.9%
MMLU: 63.36 vs 88.3 (so35)-28.2%
TruthfulQA: 55.75 vs 59 (gpt4)-5.5%
WinoGrande: 78.06 vs 87.5 (gpt4)-10.8%
GSM8K: 60.42 vs 96.4 (so35)-37.3%
LLME Score: 0.16359
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)
Candle Nous Hermes 2 Mistral 7B DPO Parameters and Internals
| LLM Name | Candle Nous Hermes 2 Mistral 7B DPO |
| Repository 🤗 | https://huggingface.co/DanielClough/Candle_Nous-Hermes-2-Mistral-7B-DPO |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 14.4 GB |
| Updated | 2025-08-24 |
| Maintainer | DanielClough |
| Model Type | mistral |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32002 |
| Torch Data Type | bfloat16 |
Best Alternatives to Candle Nous Hermes 2 Mistral 7B DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MegaBeam Mistral 7B 300K Gguf | 282K / 5 GB | 38 | 3 |
| MegaBeam Mistral 7B 300K Gguf | 282K / 5 GB | 35 | 3 |
| Mistral 7B Instruct V0.2.gguf | 32K / 14.5 GB | 7 | 3 |
| Boptruth Agatha 7B | 32K / 14.4 GB | 34 | 0 |
| Mistral 7B Instruct V0.2 GGUF | 32K / 4.4 GB | 10 | 2 |
| ...andle Mistral 7B Instruct V0.2 | 32K / 14.4 GB | 26 | 0 |
| Mahou 1.2a Mistral 7B | 32K / 14.4 GB | 25 | 7 |
| Moxin Chat 7B | 32K / 0.9 GB | 290 | 32 |
| Mistroll 7B V2.2 | 32K / 14.4 GB | 27388 | 12 |
| Mistral V0.3 7B Cybersecurity | 32K / 14.5 GB | 24 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_Nous-Hermes-2-Mistral-7B-DPO .
Rank the Candle Nous Hermes 2 Mistral 7B DPO 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? 50856 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124