Mistral 7B 3Epoch DolphinCoder is an open-source language model by Zangs3011. Features: 7b LLM, VRAM: 0.1GB, License: apache-2.0, Code Generating, HF Score: 57.5, LLM Explorer Score: 0.14, Arc: 59.2, HellaSwag: 82.3, MMLU: 57.9, TruthfulQA: 43.7, WinoGrande: 75.7, GSM8K: 26.2.
Adapter Base model:adapter:codellama/c... Base model:codellama/codellama... Code Code-llama Codegen Dataset:cognitivecomputations/... Finetuned Instruct Lora Peft Region:us
Model Card on HF 🤗: https://huggingface.co/Zangs3011/mistral_7b_3Epoch_DolphinCoder
Mistral 7b 3Epoch DolphinCoder Benchmarks
ARC: 59.22 vs 96.7 (so35)-38.8%
HellaSwag: 82.32 vs 95.3 (gpt4)-13.6%
MMLU: 57.91 vs 88.3 (so35)-34.4%
TruthfulQA: 43.7 vs 59 (gpt4)-25.9%
WinoGrande: 75.69 vs 87.5 (gpt4)-13.5%
GSM8K: 26.23 vs 96.4 (so35)-72.8%
LLME Score: 0.13562
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 3Epoch DolphinCoder Parameters and Internals
| LLM Name | Mistral 7b 3Epoch DolphinCoder |
| Repository 🤗 | https://huggingface.co/Zangs3011/mistral_7b_3Epoch_DolphinCoder |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 0.1 GB |
| Updated | 2026-04-10 |
| Maintainer | Zangs3011 |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|k_proj|v_proj|o_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Mistral 7B 3Epoch DolphinCoder
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Code Llama 7B Chatbot | 0K / 1.1 GB | 6 | 0 |
| ...10 2024 06 23 10 41 40 3558636 | 0K / 0.6 GB | 5 | 0 |
| Codellama2 Finetuned Nl2bash | 0K / 0 GB | 4 | 1 |
| Mistral 7b 2EPOCH DolphinCoder | 0K / 0.1 GB | 12 | 0 |
| Tsql To Plsql | 0K / 0.4 GB | 6 | 0 |
| Second Sql Converter Model | 0K / 0 GB | 5 | 0 |
| Llama Code 7B | 0K / 13.5 GB | 6 | 1 |
| Cria Llama2 7B V1.3 Peft | 0K / 0.1 GB | 5 | 0 |
| EvilCodeLlama 7B | 0K / 10.8 GB | 9 | 1 |
| Code Llama 7B Text To Sql | 0K / 1.8 GB | 13 | 4 |
Note: green Score (e.g. "73.2") means that the model is better than Zangs3011/mistral_7b_3Epoch_DolphinCoder .
Rank the Mistral 7B 3Epoch DolphinCoder 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? 52721 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