What are the hardware requirements for Deepseek Coder 1.3B Chat?

Deepseek Coder 1.3B Chat requires approximately 2.7 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Deepseek Coder 1.3B Chat and how large is it?

Deepseek Coder 1.3B Chat is developed by AIGym, a model with 1.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Deepseek Coder 1.3B Chat perform on standard benchmarks?

Deepseek Coder 1.3B Chat has the following published scores: MMLU 25.54. Compare against reference models on this page or on the LLM Explorer leaderboards.

Deepseek Coder 1.3B Chat by AIGym — VRAM 2.7GB, 16K context

Name: Deepseek Coder 1.3B Chat
Author: AIGym

Deepseek Coder 1.3B Chat is an open-source language model by AIGym. Features: 1.3b LLM, VRAM: 2.7GB, Context: 16K, License: apache-2.0, Fine-Tuned, Code Generating, LLM Explorer Score: 0.15, Arc: 25.6, HellaSwag: 39.7, MMLU: 25.5, GSM8K: 3.2.

Autotrain compatible Codegen Conversational Endpoints compatible Finetuned Llama Model-index Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/AIGym/deepseek-coder-1.3b-chat

Deepseek Coder 1.3B Chat Parameters and Internals

Model Type

text-generation

Use Cases

Primary Use Cases:

asking questions about code

Additional Notes

This model serves as a stepping stone for further training and improvements.

Training Details

Data Sources:

open assistant dataset

Methodology:

fine-tuned to allow it to follow direction

Input Output

Performance Tips:

The model is fine-tuned for following directions and is best used for generating responses to questions about code.

LLM Name	Deepseek Coder 1.3B Chat
Repository 🤗	https://huggingface.co/AIGym/deepseek-coder-1.3b-chat
Model Size	1.3b
Required VRAM	2.7 GB
Updated	2024-12-12
Maintainer	AIGym
Model Type	llama
Model Files	2.7 GB
Generates Code	Yes
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	16384
Model Max Length	16384
Transformers Version	4.36.2
Tokenizer Class	LlamaTokenizer
Padding Token	<pad>
Vocabulary Size	32256
Torch Data Type	bfloat16

Rank the Deepseek Coder 1.3B Chat capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Deepseek Coder 1.3B Chat

Best Alternatives	Context / RAM	Downloads	Likes
Imagine V8	16K / 2.7 GB	702	1
Deepseek Coder 1.3B Instruct	16K / 2.7 GB	92255	176
Llm4decompile 1.3B V2	16K / 2.7 GB	1272	11
...1.3B Chat And Function Calling	16K / 2.7 GB	238	0
Speechless Coder Ds 1.3B	16K / 2.7 GB	180	0
...c Deepseek Coder 1.3B Instruct	16K / 5.4 GB	5	0
CursorCore DS 1.3B SR	16K / 2.7 GB	29	2
CursorCore DS 1.3B LC	16K / 2.7 GB	27	0
CursorCore DS 1.3B	16K / 2.7 GB	9	0
Deepseek Coder 1.3B Base	16K / 2.7 GB	16806	111

Note: green Score (e.g. "73.2") means that the model is better than AIGym/deepseek-coder-1.3b-chat.