Arxiv:2305.18290 Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/ministral... Conversational Dpo Endpoints compatible Generated from trainer Instruct Mistral Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/RyanYr/self-reflect_ministral8Bit_math_dpo_iter1
Self Reflect Ministral8Bit Math DPO Iter1 Benchmarks
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)
Self Reflect Ministral8Bit Math DPO Iter1 Parameters and Internals
| LLM Name | Self Reflect Ministral8Bit Math DPO Iter1 |
| Repository 🤗 | https://huggingface.co/RyanYr/self-reflect_ministral8Bit_math_dpo_iter1 |
| Model Name | self-reflect_ministral8Bit_math_dpo_iter1 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-11-15 |
| Maintainer | RyanYr |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 131073 |
| Torch Data Type | bfloat16 |
Best Alternatives to Self Reflect Ministral8Bit Math DPO Iter1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Ministral 8B Instruct 2410 HF | 32K / 32 GB | 51015 | 10 |
| Ministrations 8B V1 | 32K / 16.1 GB | 143 | 15 |
| Ministral 8B Slerp | 32K / 29.2 GB | 27 | 0 |
| ...flect Mini8Bit Om2 460k Sft T1 | 32K / 16.1 GB | 130 | 0 |
| ...ruct 2410 MetaMathQA DPO Iter1 | 32K / 16.1 GB | 387 | 0 |
| ...t Ministral8Bit MMQA Mix Iter2 | 32K / 16.1 GB | 132 | 0 |
| ...t Ministral8Bit MMQA DPO Iter1 | 32K / 60.8 GB | 89 | 0 |
| ...ect Ministral8Bit Mg DPO Psdp2 | 32K / 16.1 GB | 69 | 0 |
| ...t Ministral8Bit MMQA DPO Iter1 | 32K / 16.1 GB | 42 | 0 |
| ...ruct 2410 MetaMathQA DPO Iter2 | 32K / 16.1 GB | 78 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/self-reflect_ministral8Bit_math_dpo_iter1 .
Rank the Self Reflect Ministral8Bit Math DPO Iter1 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217