From 3d12d2037c83f9d5d3ae832e97311b29547532e1 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@users.noreply.github.com>
Date: Thu, 26 Sep 2024 11:19:26 +0200
Subject: [PATCH] models(gallery): add llama-3.2 3B and 1B (#3671)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
 gallery/index.yaml | 60 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 9b8a0220..de38c3d5 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,64 @@
 ---
+## llama3.2
+- &llama32
+  url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
+  icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png
+  license: llama3.2
+  description: |
+    The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
+
+    Model Developer: Meta
+
+    Model Architecture: Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
+  tags:
+    - llm
+    - gguf
+    - gpu
+    - cpu
+    - llama3.2
+  name: "llama-3.2-1b-instruct:q4_k_m"
+  urls:
+    - https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF
+  overrides:
+    parameters:
+      model: llama-3.2-1b-instruct-q4_k_m.gguf
+  files:
+    - filename: llama-3.2-1b-instruct-q4_k_m.gguf
+      sha256: 1d0e9419ec4e12aef73ccf4ffd122703e94c48344a96bc7c5f0f2772c2152ce3
+      uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
+- !!merge <<: *llama32
+  name: "llama-3.2-3b-instruct:q4_k_m"
+  urls:
+    - https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF
+  overrides:
+    parameters:
+      model: llama-3.2-3b-instruct-q4_k_m.gguf
+  files:
+    - filename: llama-3.2-3b-instruct-q4_k_m.gguf
+      sha256: c55a83bfb6396799337853ca69918a0b9bbb2917621078c34570bc17d20fd7a1
+      uri: huggingface://hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF/llama-3.2-3b-instruct-q4_k_m.gguf
+- !!merge <<: *llama32
+  name: "llama-3.2-3b-instruct:q8_0"
+  urls:
+    - https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF
+  overrides:
+    parameters:
+      model: llama-3.2-3b-instruct-q8_0.gguf
+  files:
+    - filename: llama-3.2-3b-instruct-q8_0.gguf
+      sha256: 51725f77f997a5080c3d8dd66e073da22ddf48ab5264f21f05ded9b202c3680e
+      uri: huggingface://hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF/llama-3.2-3b-instruct-q8_0.gguf
+- !!merge <<: *llama32
+  name: "llama-3.2-1b-instruct:q8_0"
+  urls:
+    - https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF
+  overrides:
+    parameters:
+      model: llama-3.2-1b-instruct-q8_0.gguf
+  files:
+    - filename: llama-3.2-1b-instruct-q8_0.gguf
+      sha256: ba345c83bf5cc679c653b853c46517eea5a34f03ed2205449db77184d9ae62a9
+      uri: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF/llama-3.2-1b-instruct-q8_0.gguf
 ## Qwen2.5
 - &qwen25
   name: "qwen2.5-14b-instruct"