Mistral 7B Selfplay V0 is an open-source language model by azarafrooz. Features: 7b LLM, VRAM: 0.2GB, License: apache-2.0, Instruction-Based, HF Score: 57.8, LLM Explorer Score: 0.14, Arc: 54.7, HellaSwag: 75.7, MMLU: 55.4, TruthfulQA: 56.3, WinoGrande: 73.6, GSM8K: 31.2.
Arxiv:1910.09700 Adapter Base model:adapter:mistralai/m... Base model:mistralai/mistral-7... Dataset:argilla/openhermespref... Finetuned Instruct Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/azarafrooz/mistral-7b-selfplay-v0
Mistral 7B Selfplay V0 Benchmarks
ARC: 54.69 vs 96.7 (so35)-43.4%
HellaSwag: 75.69 vs 95.3 (gpt4)-20.6%
MMLU: 55.4 vs 88.3 (so35)-37.3%
TruthfulQA: 56.28 vs 59 (gpt4)-4.6%
WinoGrande: 73.64 vs 87.5 (gpt4)-15.8%
GSM8K: 31.24 vs 96.4 (so35)-67.6%
LLME Score: 0.14231
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 Selfplay V0 Parameters and Internals
| LLM Name | Mistral 7B Selfplay V0 |
| Repository 🤗 | https://huggingface.co/azarafrooz/mistral-7b-selfplay-v0 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.2 GB |
| Updated | 2026-04-25 |
| 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 | k_proj|q_proj|down_proj|gate_proj|up_proj|v_proj|o_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Mistral 7B Selfplay V0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Megumin | 0K / 0.1 GB | 4 | 1 |
| Deepthink Reasoning Adapter | 0K / 0.2 GB | 6 | 3 |
| Mistral 7B Instruct Sa V0.1 | 0K / 0 GB | 8 | 0 |
| Qwen2.5 7b NotesCorrector | 0K / 0.6 GB | 10 | 0 |
| Mistral 7B V2 Selfplay | 0K / 0.2 GB | 10 | 0 |
| ...82 6142 45d8 9455 Bc68ca4866eb | 0K / 1.2 GB | 5 | 0 |
| Text To Rule Mistral 2 | 0K / 0.3 GB | 5 | 0 |
| ...Sql Flash Attention 2 Dataeval | 0K / 1.9 GB | 10 | 3 |
| ...al 7B Instruct V0.3 1719301256 | 0K / 0.9 GB | 9 | 0 |
| ...al 7B Instruct V0.3 1719246505 | 0K / 0 GB | 16 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than azarafrooz/mistral-7b-selfplay-v0 .
Rank the Mistral 7B Selfplay V0 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? 53472 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