Meta's Llama 3.2 goes small with 1B and 3B models.
73M Pulls 63 Tags Updated 1 year ago
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
3.4M Pulls 49 Tags Updated 1 year ago
AI-powered coding assistant built on CodeLlama 13B. Boost productivity 4-6x with intelligent code generation, debugging, and multi-language support
156 Pulls 1 Tag Updated 8 months ago
CodeLlama-13B-QML is a large language model customized by the Qt Company for Fill-In-The-Middle code completion tasks in the QML programming language, especially for Qt Quick Controls compliant with Qt 6 releases.
2,456 Pulls 1 Tag Updated 11 months ago
The unofficial implementation of Lawyer LLaMA, with a quantization Q4_0
697 Pulls 1 Tag Updated 1 year ago
GGUF quantization of Llama 13B model that is instruction fine-tuned on medical Q/A.
266 Pulls 1 Tag Updated 2 years ago
Specialized CodeLlama variant fine-tuned specifically for Python code generation. 13B params, Q6_K quant (very high quality, minimal loss).
549 Pulls 1 Tag Updated 4 months ago
1,196 Pulls 1 Tag Updated 2 years ago
KoboldAI/LLaMA2-13B-Tiefighter
624 Pulls 2 Tags Updated 1 year ago
quantization of flozi00/Llama-2-13b-german-assistant-v7 - a finetune on german instructions and conversations in style of Alpaca
478 Pulls 1 Tag Updated 2 years ago
German finetune of Llama 2 13B.
291 Pulls 1 Tag Updated 2 years ago
Tiefighter finetune of LLaMa2-13b from KoboldAI team.
218 Pulls 1 Tag Updated 1 year ago
133 Pulls 1 Tag Updated 2 years ago
Llama2 13B in Lithuanian (Instruct)
49 Pulls 1 Tag Updated 1 year ago
18 Pulls 1 Tag Updated 2 years ago
Llama2 13B in Lithuanian (Non-Instruct)
16 Pulls 1 Tag Updated 1 year ago
8 Pulls 1 Tag Updated 2 years ago
43.3K Pulls 11 Tags Updated 1 year ago
Fast Reasoning Llama 3.2 1B model
39 Pulls 1 Tag Updated 4 months ago