From 164abb8c9fcc278425401b387e434576da607a5c Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 10 Oct 2024 19:13:47 +0200 Subject: [PATCH] models(gallery): add fireball-meta-llama-3.2-8b-instruct-agent-003-128k-code-dpo (#3784) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index d262162c..77d8e68b 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -169,6 +169,19 @@ - filename: Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf sha256: 49a4861c094d94ef5faa33f69b02cd132bb0167f1c3ca59059404f85f61e1d12 uri: huggingface://QuantFactory/Llama-3.2-3B-Agent007-Coder-GGUF/Llama-3.2-3B-Agent007-Coder.Q4_K_M.gguf +- !!merge <<: *llama32 + name: "fireball-meta-llama-3.2-8b-instruct-agent-003-128k-code-dpo" + urls: + - https://huggingface.co/QuantFactory/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO-GGUF + description: | + The LLM model is a quantized version of EpistemeAI/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO, which is an experimental and revolutionary fine-tune with DPO dataset to allow LLama 3.1 8B to be an agentic coder. It has some built-in agent features such as search, calculator, and ReAct. Other noticeable features include self-learning using unsloth, RAG applications, and memory. The context window of the model is 128K. It can be integrated into projects using popular libraries like Transformers and vLLM. The model is suitable for use with Langchain or LLamaIndex. The model is developed by EpistemeAI and licensed under the Apache 2.0 license. + overrides: + parameters: + model: Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO.Q4_K_M.gguf + files: + - filename: Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO.Q4_K_M.gguf + sha256: 7f45fa79bc6c9847ef9fbad08c3bb5a0f2dbb56d2e2200a5d37b260a57274e55 + uri: huggingface://QuantFactory/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO-GGUF/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO.Q4_K_M.gguf - &qwen25 ## Qwen2.5 name: "qwen2.5-14b-instruct"