Qwen1.5 7B Dutch Chat Sft By robinsmits: Benchmarks, Features and Detailed Analysis. Insights on Qwen1.5 7B Dutch Chat Sft.

Arxiv:2309.16609 Adapter Base model:adapter:qwen/qwen1.... Base model:qwen/qwen1.5-7b-cha... Conversational Dataset:bramvanroy/ultrachat 2... Finetuned Generated from trainer Lora Nl Peft Qwen2 Region:us Safetensors Sft Tensorboard Trl

Model Card on HF 🤗: https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat-Sft

Qwen1.5 7B Dutch Chat Sft Benchmarks

ARC: 50.68 vs 96.7 (so35)^-47.6%

HellaSwag: 73.49 vs 95.3 (gpt4)^-22.9%

MMLU: 60.47 vs 88.3 (so35)^-31.5%

TruthfulQA: 43.89 vs 59 (gpt4)^-25.6%

WinoGrande: 68.75 vs 87.5 (gpt4)^-21.4%

GSM8K: 29.34 vs 96.4 (so35)^-69.6%

LLME Score: 0.17064

^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)

Qwen1.5 7B Dutch Chat Sft (robinsmits/Qwen1.5-7B-Dutch-Chat-Sft)

🌟 Advertise your project 🚀

Qwen1.5 7B Dutch Chat Sft Parameters and Internals

Model Type

text-generation, conversational

Use Cases

Areas:

research

Applications:

conversational AI

Primary Use Cases:

Assistant and chatbot applications

Limitations:

Bias and hallucinations, Non-commercial use due to dataset restrictions

Considerations:

Perform necessary testing and validation.

Additional Notes

This finetuned model is customized for Dutch language capabilities.

Supported Languages

nl (primary)

Training Details

Data Sources:

BramVanroy/ultrachat_200k_dutch

Data Volume:

200k samples

Methodology:

Finetuning

Training Time:

28 hours (split into two 14-hour sessions)

Hardware Used:

Google Colab PRO A100 - 40GB

Model Architecture:

Adapter model based on Qwen1.5-7B-Chat

Input Output

Input Format:

Chat template format with role indicators

Accepted Modalities:

text

Output Format:

Generated text

LLM Name	Qwen1.5 7B Dutch Chat Sft
Repository 🤗	https://huggingface.co/robinsmits/Qwen1.5-7B-Dutch-Chat-Sft
Base Model(s)	Qwen/Qwen1.5-7B-Chat Qwen/Qwen1.5-7B-Chat
Model Size	7b
Required VRAM	0.6 GB
Updated	2025-08-14
Maintainer	robinsmits
Model Files	0.6 GB 0.0 GB
Supported Languages	nl
Model Architecture	Adapter
License	cc-by-nc-4.0
Model Max Length	32768
Is Biased	none
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	down_proj\|o_proj\|k_proj\|gate_proj\|v_proj\|q_proj\|up_proj
LoRA Alpha	16
LoRA Dropout	0.05
R Param	64
Errors	replace

Best Alternatives to Qwen1.5 7B Dutch Chat Sft

Best Alternatives	Context / RAM	Downloads	Likes
Qwen Megumin	0K / 0.1 GB	6	1
Uk Fraud Chatbot Llama2	0K / 0.4 GB	5	0
...s 25 Mistral 7B Irca DPO Pairs	0K / 0.1 GB	5	0
Qwen1.5 7B Chat Sa V0.1	0K / 0 GB	6	0
Zephyr 7B Ipo 0K 15K I1	0K / 0.7 GB	7	0
Hr Other 7B Lora	0K / 0.2 GB	30	0
Deepseek Llm 7B Chat Sa V0.1	0K / 0 GB	5	0
Deepthink Reasoning Adapter	0K / 0.2 GB	3	3
... Days Of Sodom LoRA Mistral 7B	0K / 0.2 GB	5	0
Mistral 7B Instruct Sa V0.1	0K / 0 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than robinsmits/Qwen1.5-7B-Dutch-Chat-Sft.

Rank the Qwen1.5 7B Dutch Chat Sft 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? 51387 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 v20241124

Support LLM Explorer

Qwen1.5 7B Dutch Chat Sft by robinsmits

» All LLMs » robinsmits » Qwen1.5 7B Dutch Chat Sft URL Share it on

Qwen1.5 7B Dutch Chat Sft Benchmarks

Qwen1.5 7B Dutch Chat Sft Parameters and Internals

Best Alternatives to Qwen1.5 7B Dutch Chat Sft

Rank the Qwen1.5 7B Dutch Chat Sft Capabilities

What open-source LLMs or SLMs are you in search of? 51387 in total.