Speechless Codellama Dolphin Orca Platypus 13B by uukuguy

 Β»  All LLMs  Β»  uukuguy  Β»  Speechless Codellama Dolphin Orca Platypus 13B   URL Share it on

Speechless Codellama Dolphin Orca Platypus 13B is an open-source language model by uukuguy. Features: 13b LLM, VRAM: 26GB, Context: 16K, License: llama2, Code Generating, HF Score: 46.7, LLM Explorer Score: 0.13, Arc: 44.8, HellaSwag: 68.6, MMLU: 44, TruthfulQA: 46.3, WinoGrande: 66.9, GSM8K: 9.6.

  Arxiv:2308.12950   Code   Codegen   Dataset:ehartford/dolphin Dataset:garage-baind/open-plat...   Dataset:open-orca/openorca   En   Endpoints compatible   Llama   Llama2   Pytorch   Region:us   Sharded

Speechless Codellama Dolphin Orca Platypus 13B Benchmarks

Speechless Codellama Dolphin Orca Platypus 13B (uukuguy/speechless-codellama-dolphin-orca-platypus-13b)
🌟 Advertise your project πŸš€

Speechless Codellama Dolphin Orca Platypus 13B Parameters and Internals

Model Type 
text generation, code synthesis
Use Cases 
Areas:
commercial, research
Applications:
general code synthesis, code understanding, Python programming, instruction following
Primary Use Cases:
code completion, infilling
Limitations:
May produce inaccurate or objectionable responses, Not fully evaluated for non-English languages
Considerations:
Careful safety evaluation before deployment
Additional Notes 
Trained with 400K GPU hours on Meta’s Research Super Cluster.
Supported Languages 
en (high proficiency), programming_languages (high proficiency)
Training Details 
Data Sources:
ehartford/dolphin, Open-Orca/OpenOrca, garage-bAInd/Open-Platypus
Methodology:
Fine-tuned with Dolphin (1% GPT4), Orca (1% GPT4), and Platypus (100%) datasets, using custom training libraries and Meta’s Research Super Cluster.
Training Time:
400K GPU hours
Hardware Used:
A100-80GB GPUs
Model Architecture:
Auto-regressive language model with an optimized transformer architecture
Responsible Ai Considerations 
Mitigation Strategies:
Developers should perform safety testing and tuning tailored to their specific applications of the model. See the Responsible Use Guide at https://ai.meta.com/llama/responsible-user-guide
Input Output 
Input Format:
Models input text only.
Accepted Modalities:
text
Output Format:
Models generate text only.
LLM NameSpeechless Codellama Dolphin Orca Platypus 13B
Repository πŸ€—https://huggingface.co/uukuguy/speechless-codellama-dolphin-orca-platypus-13b 
Model Size13b
Required VRAM26 GB
Updated2026-04-02
Maintaineruukuguy
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32016
Torch Data Typefloat16

Best Alternatives to Speechless Codellama Dolphin Orca Platypus 13B

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB103470
CodeLlama 13B Instruct Hf16K / 26 GB8910159
CodeLlama 13B MORepair16K / 26 GB22
CodeLlama 13B Hf16K / 26 GB4576118
CodeLlama 13B Hf16K / 26 GB476822
CodeLlama 13B Python Hf16K / 26 GB228051
Codellama 13B Oasst Sft V1016K / 25.9 GB256069
Tora Code 13B V1.016K / 26 GB118515
Speechless Codellama Orca 13B16K / 26 GB17582
...ma 13B Hf Truncated Embeddings16K / 52.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than uukuguy/speechless-codellama-dolphin-orca-platypus-13b.

Rank the Speechless Codellama Dolphin Orca Platypus 13B Capabilities

πŸ†˜ 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? 52473 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum β€” our secure, self-hosted AI agent for server management.
Release v20260328a