Dolphincoder Starcoder2 7B By cognitivecomputations: Benchmarks, Features and Detailed Analysis. Insights on Dolphincoder Starcoder2 7B.

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:microsoft/orca-math-wo... Dataset:teknium/openhermes En Endpoints compatible Instruct Pytorch Region:us Sharded Starcoder2

Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-7b

Dolphincoder Starcoder2 7B Benchmarks

ARC: 38.4 vs 96.7 (so35)^-60.3%

HellaSwag: 50.7 vs 95.3 (gpt4)^-46.8%

MMLU: 39.72 vs 88.3 (so35)^-55%

TruthfulQA: 43.33 vs 59 (gpt4)^-26.6%

WinoGrande: 55.96 vs 87.5 (gpt4)^-36%

GSM8K: 21.38 vs 96.4 (so35)^-77.8%

LLME Score: 0.21513

^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)

Dolphincoder Starcoder2 7B (cognitivecomputations/dolphincoder-starcoder2-7b)

Dolphincoder Starcoder2 7B Parameters and Internals

Model Type

text generation, coding assistant

Additional Notes

This model is highly effective at code generation. It has been filtered to remove alignment and bias components, resulting in high compliance with user input.

Supported Languages

en (high)

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, microsoft/orca-math-word-problems-200k

Methodology:

qLoRA and Axolotl

Training Time:

2 days on 8x L40S's

Input Output

Input Format:

ChatML

Accepted Modalities:

text

Output Format:

text

LLM Name	Dolphincoder Starcoder2 7B
Repository 🤗	https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-7b
Model Size	7b
Required VRAM	14.9 GB
Updated	2025-01-15
Maintainer	cognitivecomputations
Model Type	starcoder2
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 5.0 GB: 3-of-3
Supported Languages	en
Model Architecture	Starcoder2ForCausalLM
License	bigcode-openrail-m
Context Length	16384
Model Max Length	16384
Transformers Version	4.39.0.dev0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	49154
Torch Data Type	bfloat16
Activation Function	gelu

Quantized Models of the Dolphincoder Starcoder2 7B

Model	Likes	Downloads	VRAM
...Starcoder2 7B Bnb 4bit Smashed	0	19	4 GB

Best Alternatives to Dolphincoder Starcoder2 7B

Best Alternatives	Context / RAM	Downloads	Likes
Speechless Starcoder2 7B	16K / 14.4 GB	891	5
Starcoder2 7B Instruct	16K / 14.4 GB	176	2
Starcoder2 7B Instruct GPTQ	16K / 4.5 GB	11	1

Rank the Dolphincoder Starcoder2 7B 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? 41362 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 v20241227

Support LLM Explorer