Ntp Mathlib St Deepseek Coder 1.3B by l3lab

 ยป  All LLMs  ยป  l3lab  ยป  Ntp Mathlib St Deepseek Coder 1.3B   URL Share it on

  Arxiv:2408.03350   Autotrain compatible   Codegen   Endpoints compatible   Llama   Pytorch   Region:us

Ntp Mathlib St Deepseek Coder 1.3B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ntp Mathlib St Deepseek Coder 1.3B (l3lab/ntp-mathlib-st-deepseek-coder-1.3b)

Ntp Mathlib St Deepseek Coder 1.3B Parameters and Internals

Training Details 
Data Sources:
ntp-mathlib-instruct-st
Methodology:
Finetuned for Lean 4 tactic prediction given proof states
Input Output 
Input Format:
Example input: /- You are proving a theorem in Lean 4. You are given the following information: - The current proof state, inside [STATE]...[/STATE] Your task is to generate the next tactic in the proof. Put the next tactic inside [TAC]...[/TAC] -/ [STATE] m n : โ„• h : Nat.Coprime m n โŠข Nat.gcd m n = 1 [/STATE] [TAC]
Output Format:
Example output: rw [Nat.Coprime] at h [/TAC]
LLM NameNtp Mathlib St Deepseek Coder 1.3B
Repository ๐Ÿค—https://huggingface.co/l3lab/ntp-mathlib-st-deepseek-coder-1.3b 
Model Size1.3b
Required VRAM2.7 GB
Updated2025-01-20
Maintainerl3lab
Model Typellama
Model Files  2.7 GB
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size32256
Torch Data Typebfloat16

Best Alternatives to Ntp Mathlib St Deepseek Coder 1.3B

Best Alternatives
Context / RAM
Downloads
Likes
Deepseek Coder 1.3B Instruct16K / 2.7 GB14105103
Llm4decompile 1.3B V216K / 2.7 GB6126
...c Deepseek Coder 1.3B Instruct16K / 5.4 GB110
CursorCore DS 1.3B LC16K / 2.7 GB160
CursorCore DS 1.3B SR16K / 2.7 GB150
CursorCore DS 1.3B16K / 2.7 GB140
Deepseek Coder 1.3B Base16K / 2.7 GB5172967
Speechless Coder Ds 1.3B16K / 2.7 GB6880
Hpc Coder V2.1.3B16K / 2.7 GB144
...1.3B Chat And Function Calling16K / 2.7 GB2380
Note: green Score (e.g. "73.2") means that the model is better than l3lab/ntp-mathlib-st-deepseek-coder-1.3b.

Rank the Ntp Mathlib St Deepseek Coder 1.3B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41636 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227