Mistral 7B Orca DPO 2h By SC56: Benchmarks, Features and Detailed Analysis. Insights on Mistral 7B Orca DPO 2h.

Arxiv:1910.09700 Adapter Finetuned Lora Region:us Safetensors

Mistral 7B Orca DPO 2h Benchmarks

ARC: 73.12 vs 96.7 (so35)^-24.4%

HellaSwag: 88.65 vs 95.3 (gpt4)^-7%

MMLU: 64.99 vs 88.3 (so35)^-26.4%

TruthfulQA: 71.31 vs 59 (gpt4)^20.9%

WinoGrande: 84.21 vs 87.5 (gpt4)^-3.8%

GSM8K: 70.58 vs 96.4 (so35)^-26.8%

LLME Score: 0.18079

^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)

Mistral 7B Orca DPO 2h Parameters and Internals

LLM Name	Mistral 7B Orca DPO 2h
Repository 🤗	https://huggingface.co/SC56/Mistral-7B-orca-dpo-2h
Model Size	7b
Required VRAM	0.1 GB
Updated	2024-11-23
Maintainer	SC56
Model Files	0.1 GB
Model Architecture	Adapter
License	cc-by-4.0
Is Biased	none
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	up_proj\|o_proj\|down_proj\|v_proj\|k_proj\|gate_proj\|q_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	16

Mistral 7B Orca DPO 2h (SC56/Mistral-7B-orca-dpo-2h)

Quantized Models of the Mistral 7B Orca DPO 2h

Model	Likes	Downloads	VRAM
...andle Mistral 7B Instruct V0.2	0	41	14 GB

Best Alternatives to Mistral 7B Orca DPO 2h

Best Alternatives	Context / RAM	Downloads	Likes
CodeAstra 7B	0K / 0 GB	541	8
Qwen1.5 7B Chat Sa V0.1	0K / 0 GB	5	0
Magicoder	0K / 0 GB	10713	10
Deepseek Llm 7B Chat Sa V0.1	0K / 0 GB	5	0
...eze Embed Tokens Q V Proj Lora	0K / 0.1 GB	2	1
Glue Sst2	0K / 0 GB	10327	1
Llamaduo Synth Ds V0.1	0K / 0.2 GB	9	1
Storytell	0K / 0 GB	8	0
Zephyr 7B Gpo V5 I1	0K / 0.7 GB	6	0
Zephyr 7B Gpo V6 I1	0K / 0.7 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than SC56/Mistral-7B-orca-dpo-2h.

Rank the Mistral 7B Orca DPO 2h 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! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 38311 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Release v20241110

Support LLM Explorer