New Ollama by danielhanchen

 ยป  All LLMs  ยป  danielhanchen  ยป  New Ollama   URL Share it on

  4bit Base model:quantized:unsloth/l... Base model:unsloth/llama-3-8b-...   Conversational   En   Endpoints compatible   Gguf   Llama   Quantized   Region:us   Unsloth

New Ollama Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

New Ollama Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, llama, gguf
Training Details 
Methodology:
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameNew Ollama
Repository ๐Ÿค—https://huggingface.co/danielhanchen/new_ollama 
Base Model(s)  Llama 3 8B Bnb 4bit   unsloth/llama-3-8b-bnb-4bit
Model Size8b
Required VRAM4.9 GB
Updated2024-12-02
Maintainerdanielhanchen
Model Typellama
Model Files  16.1 GB   4.9 GB   8.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureAutoModel
Licenseapache-2.0
New Ollama (danielhanchen/new_ollama)

Best Alternatives to New Ollama

Best Alternatives
Context / RAM
Downloads
Likes
OpenMath 8B GGUF0K / 4.9 GB1477
Meta Llama 3 8B Instruct GGUF0K / 2 GB189194677
Llama 3 8B Instruct V0.10 GGUF0K / 2 GB16696502
...ma 3 8B Instruct 32K V0.1 GGUF0K / 2 GB188452256
Llama 3 8B Instruct V0.9 GGUF0K / 2 GB16622052
Llama 3 8B Instruct 64K GGUF0K / 3.2 GB175375712
Llama 3 Smaug 8B GGUF0K / 3.2 GB17311834
...ma 3 8B Instruct DPO V0.1 GGUF0K / 3.2 GB14838912
...ma 3 8B Instruct DPO V0.2 GGUF0K / 3.2 GB14838511
Granite 8B Code Instruct GGUF0K / 3.1 GB284746
Note: green Score (e.g. "73.2") means that the model is better than danielhanchen/new_ollama.

Rank the New Ollama 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? 38765 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124