LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Deepseek Coder 1.3B Chat And Function Calling by AIGym

 »  All LLMs  »  AIGym  »  Deepseek Coder 1.3B Chat And Function Calling   URL Share it on

  238   

Deepseek Coder 1.3B Chat And Function Calling 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, HF Score: 31.8, LLM Explorer Score: 0.16, Arc: 26.3, HellaSwag: 39.3, MMLU: 26.9, TruthfulQA: 43.4, WinoGrande: 51.7, GSM8K: 3.4.

  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-and-function-calling 

Deepseek Coder 1.3B Chat And Function Calling Benchmarks

ARC: 26.28 vs 96.7 (so35)-72.8%
HellaSwag: 39.27 vs 95.3 (gpt4)-58.8%
MMLU: 26.92 vs 88.3 (so35)-69.5%
TruthfulQA: 43.37 vs 59 (gpt4)-26.5%
WinoGrande: 51.7 vs 87.5 (gpt4)-40.9%
GSM8K: 3.41 vs 96.4 (so35)-96.5%
LLME Score: 0.16193
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Coder 1.3B Chat And Function Calling (AIGym/deepseek-coder-1.3b-chat-and-function-calling)
🌟 Advertise your project 🚀

Deepseek Coder 1.3B Chat And Function Calling Parameters and Internals

Model Type 
text-generation
Use Cases 
Considerations:
Use the specified template when interacting with the fine-tuned model.
Additional Notes 
The model was fine-tuned to work with OpenAI syntask and will return function when appropriate.
Training Details 
Methodology:
Fine-tuned on the open assistant dataset and function calling
LLM NameDeepseek Coder 1.3B Chat And Function Calling
Repository 🤗https://huggingface.co/AIGym/deepseek-coder-1.3b-chat-and-function-calling 
Model Size1.3b
Required VRAM2.7 GB
Updated2024-12-12
MaintainerAIGym
Model Typellama
Model Files  2.7 GB
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size32256
Torch Data Typebfloat16

Quantized Models of the Deepseek Coder 1.3B Chat And Function Calling

Model
Likes
Downloads
VRAM
...Coder 1.3B Function Calling V122152 GB

Best Alternatives to Deepseek Coder 1.3B Chat And Function Calling

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Coder 1.3B Instruct16K / 2.7 GB637760147
Llm4decompile 1.3B V216K / 2.7 GB80911
Speechless Coder Ds 1.3B16K / 2.7 GB8640
...c Deepseek Coder 1.3B Instruct16K / 5.4 GB50
Deepseek Coder 1.3B Chat16K / 2.7 GB981
CursorCore DS 1.3B SR16K / 2.7 GB92
CursorCore DS 1.3B LC16K / 2.7 GB60
CursorCore DS 1.3B16K / 2.7 GB90
Deepseek Coder 1.3B Base16K / 2.7 GB20386103
Hpc Coder V2.1.3B16K / 2.7 GB365
Note: green Score (e.g. "73.2") means that the model is better than AIGym/deepseek-coder-1.3b-chat-and-function-calling.

Rank the Deepseek Coder 1.3B Chat And Function Calling 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer