Model reference · open weights

deepseekcoder-codeqwen-align-subset

LLMs bigcode Text gen 1 build Licence not stated 144 dl/mo

deepseekcoder-codeqwen-align-subset is an open-weight language model from bigcode. deepseekcoder-33b-codeqwen-align-subset (FP32) weighs 66.7 GB; the smallest configuration that runs it is H100 80 GB.

Hugging Face ↗GitHub ↗Paper ↗

What it is

Released by	bigcode
Released	2024-05-13
Parameters	33.3B
VRAM	66.7 GB for the weights

What it runs on

Memory and cards for deepseekcoder-33b-codeqwen-align-subset (FP32)

66.7 GBweights, file size

254 MBcache per 1K tokens

737 MBruntime overhead, at least

16,384 tokenscontext max

Card	Requests at once	Context max	Memory
Card	8K each	Context max	Memory
RTX 3060 12 GB … L40S 48 GB 6 smaller cards	—	—
A100 80 GB	5	all 16K	78.2 GB
H100 80 GB	3	all 16K	78.1 GB
RTX PRO 6000 Blackwell 96 GB	11	all 16K	93.8 GB
DGX Spark (GB10) 128 GB unified	17	all 16K	107 GB
H200 141 GB	32	all 16K	138 GB
B200 180 GB	50	all 16K	176 GB
2× L40S 48 GB tensor parallel	9	all 16K	44.0 GB a card
4× RTX 4090 24 GB tensor parallel	11	all 16K	23.4 GB a card
4× RTX 3090 24 GB tensor parallel	11	all 16K	23.4 GB a card
4× RTX 5090 32 GB tensor parallel	26	all 16K	31.0 GB a card
2× H100 80 GB tensor parallel	39	all 16K	78.1 GB a card
2× A100 80 GB tensor parallel	42	all 16K	78.2 GB a card

Memory needed at each load

Requests at once	8K tokens each
1	69.5 GB
5	77.8 GB
8	84.1 GB
16	101 GB
32	134 GB
64	201 GB

One card, with vLLM's small-card settings.

From the model card

What bigcode says about deepseekcoder-codeqwen-align-subset

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Read the full model card

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

Details

Type	Language models
Task	Text gen
Context	16,384 tokens
Runs with	transformers
Popularity	144 downloads / month
Weights	66.7 GB, deepseekcoder-33b-codeqwen-align-subset (FP32, file size)