CodeQwen1.5 7B By Qwen: Benchmarks, Features and Detailed Analysis. Insights on CodeQwen1.5 7B.

Autotrain compatible En Endpoints compatible Pretrained Qwen2 Region:us Safetensors Sharded Tensorflow

CodeQwen1.5 7B Benchmarks

HumanEval AVG: 40.47^0%

Python Eval: 50.79^-24.2%

Java Eval: 42.15^0%

Javascript Eval: 50.07^0%

Racket Eval: 24.89^0%

Rust Eval: 47.56^0%

Swift Eval: 43.33^0%

^nn.n% — How the model compares to the GPT-4.

CodeQwen1.5 7B Parameters and Internals

LLM Name	CodeQwen1.5 7B
Repository	Open on 🤗
Model Size	7b
Required VRAM	14.6 GB
Updated	2024-07-27
Maintainer	Qwen
Model Type	qwen2
Model Files	3.9 GB: 1-of-4 4.0 GB: 2-of-4 4.0 GB: 3-of-4 2.7 GB: 4-of-4
Supported Languages	en
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	65536
Model Max Length	65536
Transformers Version	4.39.3
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<fim_pad>
Vocabulary Size	92416
Torch Data Type	bfloat16

Quantized Models of the CodeQwen1.5 7B

Model	Likes	Downloads	VRAM
CodeQwen1.5 7B AWQ	2	88	5 GB
CodeQwen1.5 7B EXL2 8.0bpw	1	10	7 GB

Best Alternatives to CodeQwen1.5 7B

Best Alternatives	HF Rank	Context/RAM	Downloads	Likes
Qwen2 7B	0.5	128K / 15.4 GB	159715	102
Einstein V7 Qwen2 7B	0.4	128K / 15.2 GB	2168	32
Qwen2 7B Instruct V0.8	0.4	128K / 15.2 GB	40990	3
Dolphin 2.9.2 Qwen2 7B	0.4	128K / 15.2 GB	4242	54
Calme 2.8 Qwen2 7B	0.3	128K / 15.2 GB	41039	4
Qwen2 7B Instruct V0.5	0.3	128K / 15.2 GB	41019	1
Calme 2.5 Qwen2 7B	0.3	128K / 15.2 GB	41032	1
Calme 2.4 Qwen2 7B	0.3	128K / 15.2 GB	41022	1
Qwen2 7B Instruct V0.4	0.3	128K / 15.2 GB	41008	1
Calme 2.7 Qwen2 7B	0.3	128K / 15.2 GB	40985	1

Note: green Score (e.g. "73.2") means that the model is better than Qwen/CodeQwen1.5-7B.

Rank the CodeQwen1.5 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? 34446 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 v2024072501

Support LLM Explorer