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

Open Llama 3B V2 Python Instruct 0.1 4bit by balrogbob

 »  All LLMs  »  balrogbob  »  Open Llama 3B V2 Python Instruct 0.1 4bit   URL Share it on

  7   
  4-bit   4bit   Autotrain compatible Base model:openlm-research/ope... Base model:quantized:openlm-re...   Bitsandbytes   En   Endpoints compatible   Instruct   Llama   Quantized   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/balrogbob/open_llama_3b_v2-python-instruct-0.1_4bit 

Open Llama 3b V2 Python Instruct 0.1 4bit Benchmarks

ARC: 46.6 vs 96.7 (so35)-51.8%
HellaSwag: 68.2 vs 95.3 (gpt4)-28.4%
MMLU: 27.3 vs 88.3 (so35)-69.1%
TruthfulQA: 34.78 vs 59 (gpt4)-41.1%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 3.1 vs 96.4 (so35)-96.8%
OpenCompas: 34.6 vs 73.3 (gpt4)-52.8%
Exam: 31 vs 77.2 (gpt4)-59.8%
Language: 33.2 vs 62 (gpt4)-46.5%
Knowledge: 42.1 vs 73.5 (gpt4)-42.7%
Understand: 33.2 vs 70 (gpt4)-52.6%
Reasoning: 34.4 vs 74.4 (gpt4)-53.8%
LLME Score: 0.20354
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Open Llama 3B V2 Python Instruct 0.1 4bit (balrogbob/open_llama_3b_v2-python-instruct-0.1_4bit)
🌟 Advertise your project 🚀

Open Llama 3B V2 Python Instruct 0.1 4bit Parameters and Internals

Model Type 
text-generation-inference, transformers, llama, trl, sft
Supported Languages 
en ()
Training Details 
Methodology:
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameOpen Llama 3b V2 Python Instruct 0.1 4bit
Repository 🤗https://huggingface.co/balrogbob/open_llama_3b_v2-python-instruct-0.1_4bit 
Base Model(s)  Open Llama 3b V2   openlm-research/open_llama_3b_v2
Model Size3b
Required VRAM2.5 GB
Updated2025-09-23
Maintainerbalrogbob
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.42.4
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Quantized Models of the Open Llama 3B V2 Python Instruct 0.1 4bit

Model
Likes
Downloads
VRAM
...ma 3b V2 Python Instruct 0.1.2056 GB

Best Alternatives to Open Llama 3B V2 Python Instruct 0.1 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...ama Llama 3.2 3B Instruct FP16128K / 6.5 GB27238447
...2 3B Instruct Unsloth Bnb 4bit128K / 2.4 GB11558410
Llama32 3B En Emo 2000 Stp128K / 2.2 GB1430
Security Llama3.2 3B128K / 6.5 GB6510
Llama32 3B En Emo 300 Stp128K / 2.2 GB100
Llama32 3B En Emo 1000 Stp128K / 2.2 GB50
Llama32 3B En Emo 5000 Stp128K / 2.2 GB70
...ngCore 3B Instruct R01 Reflect128K / 6.5 GB01
ReasoningCore 3B 0128K / 6.5 GB112
Llama 3.2 3B Unsloth Bnb 4bit128K / 2.4 GB300382
Note: green Score (e.g. "73.2") means that the model is better than balrogbob/open_llama_3b_v2-python-instruct-0.1_4bit.

Rank the Open Llama 3B V2 Python Instruct 0.1 4bit 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? 51544 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.
Release v20241124
  Support LLM Explorer