Mistral 7B V2 Selfplay is an open-source language model by azarafrooz. Features: 7b LLM, VRAM: 0.2GB, License: apache-2.0, Instruction-Based, HF Score: 65.7, LLM Explorer Score: 0.14, Arc: 63, HellaSwag: 85, MMLU: 60.7, TruthfulQA: 68.2, WinoGrande: 77.4, GSM8K: 39.8.
Arxiv:1910.09700 Adapter Base model:adapter:mistralai/m... Base model:mistralai/mistral-7... Dataset:dibt/10k prompts ranke... Finetuned Instruct Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/azarafrooz/mistral-7b-v2-selfplay
Mistral 7B V2 Selfplay Benchmarks
ARC: 62.97 vs 96.7 (so35)-34.9%
HellaSwag: 84.97 vs 95.3 (gpt4)-10.8%
MMLU: 60.71 vs 88.3 (so35)-31.2%
TruthfulQA: 68.24 vs 59 (gpt4)15.7%
WinoGrande: 77.35 vs 87.5 (gpt4)-11.6%
GSM8K: 39.8 vs 96.4 (so35)-58.7%
LLME Score: 0.14281
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 V2 Selfplay Parameters and Internals
| LLM Name | Mistral 7B V2 Selfplay |
| Repository 🤗 | https://huggingface.co/azarafrooz/mistral-7b-v2-selfplay |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.2 GB |
| Updated | 2026-04-01 |
| Maintainer | azarafrooz |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|o_proj|gate_proj|k_proj|v_proj|q_proj|up_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Mistral 7B V2 Selfplay
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Megumin | 0K / 0.1 GB | 3 | 1 |
| Deepthink Reasoning Adapter | 0K / 0.2 GB | 3 | 3 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 5 | 0 |
| Qwen2.5 7b NotesCorrector | 0K / 0.6 GB | 10 | 0 |
| Mistral 7B Selfplay V0 | 0K / 0.2 GB | 6 | 0 |
| Mistral 7B V0.1 Emotion | 0K / 1.3 GB | 225 | 1 |
| ...82 6142 45d8 9455 Bc68ca4866eb | 0K / 1.2 GB | 5 | 0 |
| ...Sql Flash Attention 2 Dataeval | 0K / 1.9 GB | 9 | 3 |
| Text To Rule Mistral 2 | 0K / 0.3 GB | 5 | 0 |
| ...al 7B Instruct V0.3 1719301256 | 0K / 0.9 GB | 9 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than azarafrooz/mistral-7b-v2-selfplay .
Rank the Mistral 7B V2 Selfplay 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? 52473 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