Llama 2 13B · Ollama

llama3.2

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

81.8M Pulls 63 Tags Updated 1 year ago

Cheatmeal/lollama13b

Llama2 13B in Lithuanian (Instruct)

50 Pulls 1 Tag Updated 1 year ago

Cheatmeal/lollama13balfa

Llama2 13B in Lithuanian (Non-Instruct)

16 Pulls 1 Tag Updated 1 year ago

HammerAI/llama2-tiefighter

KoboldAI/LLaMA2-13B-Tiefighter

647 Pulls 2 Tags Updated 2 years ago

localmind/sauerkrautlm

German finetune of Llama 2 13B.

308 Pulls 1 Tag Updated 2 years ago

huihui_ai/llama3.2-abliterate

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

47.9K Pulls 11 Tags Updated 1 year ago

tomtyiu/Reasoning-Llama-3.2-1B

Fast Reasoning Llama 3.2 1B model

47 Pulls 1 Tag Updated 7 months ago

pdesj/Llama-3.2-1B-nba-ner-GGUF

Fine-tuned version of Llama 3.1 1B, optimized for NER tasks on NBA sentences containing player and team names.

tools

20 Pulls 1 Tag Updated 8 months ago

alkindivv/Llama-3.2-1B-Indo

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct that has been optimized for Indonesian language understanding and generation. The fine-tuning process utilized Low-Rank Adaptation (LoRA) to efficiently adapt the model while minimizi

157 Pulls 1 Tag Updated 1 year ago

lakomoor/vikhr-llama-3.2-1b-instruct

Instructive model based on Llama-3.2-1B-Instruct, trained on the Russian-language dataset GrandMaster-PRO-MAX. It is 5 times more efficient than the base model, making it perfect for deployment on low-power or mobile devices.

1b

15.2K Pulls 8 Tags Updated 1 year ago

sadiq-bd/llama3.2-1b-uncensored

An uncensored version of the original Llama-3.2-1B-Instruct, created via abliteration

tools

3,073 Pulls 1 Tag Updated 1 year ago

rscr/vikhr_llama3.2_1b

Vikhr-Llama-3.2-1B-Instruct

tools

538 Pulls 1 Tag Updated 1 year ago

R4C3R/llama3.2-1b-heretic

A decensored multilingual 1B Llama 3.2 model with suppressed refusal behavior. Made by RACER IS OP.

tools

148 Pulls 4 Tags Updated 1 month ago

adhishtanaka/llama_3.2_1b-SQL

This is a fine-tuned llama 3.2 model with 1 billion parameters. It turns plain English questions into SQL queries. It was trained using examples of questions and their matching SQL, making it easier to work with databases using natural language.

110 Pulls 1 Tag Updated 1 year ago