Autotrain compatible Conversational Endpoints compatible Gguf Mistral Q4 Quantized Region:us Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/DanielClough/Candle_Snorkel-Mistral-PairRM-DPO
Candle Snorkel Mistral PairRM DPO Benchmarks
ARC: 65.96 vs 96.7 (so35)-31.8%
HellaSwag: 85.63 vs 95.3 (gpt4)-10.1%
MMLU: 60.85 vs 88.3 (so35)-31.1%
TruthfulQA: 70.91 vs 59 (gpt4)20.2%
WinoGrande: 77.58 vs 87.5 (gpt4)-11.3%
GSM8K: 36.16 vs 96.4 (so35)-62.5%
LLME Score: 0.15841
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 Snorkel Mistral PairRM DPO Parameters and Internals
| LLM Name | Candle Snorkel Mistral PairRM DPO |
| Repository 🤗 | https://huggingface.co/DanielClough/Candle_Snorkel-Mistral-PairRM-DPO |
| Base Model(s) | |
| Required VRAM | 14.4 GB |
| Updated | 2025-07-31 |
| 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 | 4.34.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Candle Snorkel Mistral PairRM DPO
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...istral Nemo Instruct 2407 GGUF | 1000K / 4.8 GB | 4912 | 66 |
| ...istral Nemo Instruct 2407 GGUF | 1000K / 4.8 GB | 954 | 8 |
| Devstral Small 2505 GGUF | 128K / 0.9 GB | 21830 | 101 |
| ...istral C64Wizard Instruct GGUF | 32K / 4.4 GB | 11 | 0 |
| Mistral 7B1.0 GGUF | 32K / 5.1 GB | 5 | 0 |
| Equall Saul Instruct V1 | 32K / 5.1 GB | 6 | 0 |
| Candle MistralTrix V1 | 32K / 17.9 GB | 85 | 0 |
| AI G Expander V5 GGUF | 32K / 4.4 GB | 5 | 0 |
| Candle Tiny Mistral | 32K / 0.4 GB | 57 | 0 |
| MHENN4 GGUF | 32K / 4.4 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_Snorkel-Mistral-PairRM-DPO .
Rank the Candle Snorkel Mistral PairRM 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? 50299 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124