LLM EXPLORER 59,420 MODELS INDEXED

Dolphincoder Starcoder2 15B by cognitivecomputations

By cognitivecomputations · 84 downloads
HF Repo ↗ Copy URL

Dolphincoder Starcoder2 15B is an open-source language model by cognitivecomputations. Features: 15b LLM, VRAM: 31.9GB, Context: 16K, License: bigcode-openrail-m, Instruction-Based, LLM Explorer Score: 0.12.

  Autotrain compatible   Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:jondurbin/airoboros-2....   Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil...   Dataset:teknium/openhermes   En   Endpoints compatible   Instruct   Pytorch   Region:us   Sharded   Starcoder2
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b 

Dolphincoder Starcoder2 15B Parameters and Internals

Model Type 
code generation, programming assistant
Additional Notes 
The model is highly compliant and should be used with an alignment layer to prevent unethical uses.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
cognitivecomputations/dolphin, jondurbin/airoboros-2.2.1, cognitivecomputations/dolphin-coder, teknium/openhermes, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, m-a-p/Code-Feedback, m-a-p/CodeFeedback-Filtered-Instruction
Methodology:
qLoRA and Axolotl
Training Time:
3 days
Hardware Used:
8x H100s
Responsible Ai Considerations 
Transparency:
Users must implement an alignment layer to ensure compliance with ethical standards.
Accountability:
Users are responsible for the model's outputs and should ensure compliance through an alignment layer.
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
programs in various languages
Performance Tips:
Use an alignment layer to ensure compliance with ethical guidelines.
LLM NameDolphincoder Starcoder2 15B
Repository 🤗https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b 
Model Size15b
Required VRAM31.9 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typestarcoder2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   2.0 GB: 7-of-7
Supported Languagesen
Model ArchitectureStarcoder2ForCausalLM
Licensebigcode-openrail-m
Context Length16384
Model Max Length16384
Transformers Version4.39.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49154
Torch Data Typebfloat16

Best Alternatives to Dolphincoder Starcoder2 15B

Best Alternatives
Context / RAM
Downloads
Likes
Starcoder2 15B Instruct V0.116K / 31.9 GB597105
Starcoder2 15B Instruct V0.116K / 53.4 GB250
Dolphincoder Starcoder2 15B16K / 31.9 GB1768
Starcoder2 15B Instruct16K / 31.9 GB67
...rCoder2 15B Instruct V0.1 GGUF16K / 6.2 GB4120
...rCoder2 15B Instruct V0.1 GGUF16K / 6.2 GB2610
Starcoder2 15B Instruct GPTQ16K / 9.2 GB22
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphincoder-starcoder2-15b.