From 3571940a9a6b8767f17046051b90b0a0c95cf930 Mon Sep 17 00:00:00 2001 From: Yingbei Date: Tue, 2 Jul 2024 16:04:08 -0700 Subject: [PATCH 1/4] update submodules --- rubra-tools | 2 +- tools.cpp | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/rubra-tools b/rubra-tools index c9d4eef..498cd27 160000 --- a/rubra-tools +++ b/rubra-tools @@ -1 +1 @@ -Subproject commit c9d4eefbcc6591b92bf6134a38eadb0f2e2c1c23 +Subproject commit 498cd27c213f10f7bfe1f392abd81606c82f209e diff --git a/tools.cpp b/tools.cpp index 07370f4..04dc552 160000 --- a/tools.cpp +++ b/tools.cpp @@ -1 +1 @@ -Subproject commit 07370f4a3c446dc47b414ebc4cf9ac0f78ee111a +Subproject commit 04dc552d170b8b5816988c9ab1ad3e6b21711eb9 From 1b03efd86d08c75846c276c13b252a0035fa002c Mon Sep 17 00:00:00 2001 From: Yingbei Date: Tue, 2 Jul 2024 16:06:59 -0700 Subject: [PATCH 2/4] update --- tools.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools.cpp b/tools.cpp index 04dc552..89971d6 160000 --- a/tools.cpp +++ b/tools.cpp @@ -1 +1 @@ -Subproject commit 04dc552d170b8b5816988c9ab1ad3e6b21711eb9 +Subproject commit 89971d6b96ae5e9f3c16ebe839d6d85d8189846f From 76b1488c6f4b9b2bfe083a65b0b159338025d6a3 Mon Sep 17 00:00:00 2001 From: Yingbei Date: Tue, 2 Jul 2024 16:30:06 -0700 Subject: [PATCH 3/4] update llama.cpp docs --- docs/docs/inference/llamacpp.mdx | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/docs/inference/llamacpp.mdx b/docs/docs/inference/llamacpp.mdx index 70d6d20..9f222f5 100644 --- a/docs/docs/inference/llamacpp.mdx +++ b/docs/docs/inference/llamacpp.mdx @@ -52,6 +52,14 @@ For example: wget https://huggingface.co/rubra-ai/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/rubra-meta-llama-3-8b-instruct.Q8_0.gguf ``` +:::info +For large multi-part model files, such as [rubra-meta-llama-3-70b-instruct_Q6_K-0000*-of-00003.gguf](https://huggingface.co/rubra-ai/Meta-Llama-3-70B-Instruct-GGUF/tree/main), use the following command to merge them before proceeding to the next step: +``` +./llama-gguf-split --merge rubra-meta-llama-3-70b-instruct_Q6_K-0000*-of-00003.gguf rubra-meta-llama-3-70b-instruct_Q6_K.gguf +``` +This will merge multi-part model files to one gguf file `rubra-meta-llama-3-70b-instruct_Q6_K.gguf`. +::: + ### 5. Start the OpenAI Compatible Server ```bash From f9ad0517dbdbb3e5aaa8851180152c3a102f056d Mon Sep 17 00:00:00 2001 From: Yingbei Date: Tue, 2 Jul 2024 18:07:27 -0700 Subject: [PATCH 4/4] update links in readme_CN to modelscope --- README_CN.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/README_CN.md b/README_CN.md index 6196f53..9d61424 100644 --- a/README_CN.md +++ b/README_CN.md @@ -16,13 +16,13 @@ Rubra 增强了当前最流行的一系列开放权重大模型（LLM）的工 | 模型 | 最大上下文长度 | 大小 | 基础模型发布者 | |---------------------------------------------------------------|----------------|------|----------------------| -| [rubra-ai/Meta-Llama-3-8B-Instruct](https://huggingface.co/rubra-ai/Meta-Llama-3-8B-Instruct) | 8,000 | 8B | Meta | -| [rubra-ai/Meta-Llama-3-70B-Instruct](https://huggingface.co/rubra-ai/Meta-Llama-3-70B-Instruct) | 8,000 | 70B | Meta | -| [rubra-ai/gemma-1.1-2b-it](https://huggingface.co/rubra-ai/gemma-1.1-2b-it) | 8,192 | 2B | Google | -| [rubra-ai/Mistral-7B-Instruct-v0.3](https://huggingface.co/rubra-ai/Mistral-7B-Instruct-v0.3) | 32,000 | 7B | Mistral | -| [rubra-ai/Mistral-7B-Instruct-v0.2](https://huggingface.co/rubra-ai/Mistral-7B-Instruct-v0.2) | 32,000 | 7B | Mistral | -| [rubra-ai/Phi-3-vision-128k-instruct](https://huggingface.co/rubra-ai/Phi-3-vision-128k-instruct)| 128,000 | 3B | Microsoft | -| [rubra-ai/Qwen2-7B-Instruct](https://huggingface.co/rubra-ai/Qwen2-7B-Instruct) | 131,072 | 7B | Qwen | +| [rubra-ai/Meta-Llama-3-8B-Instruct](https://www.modelscope.cn/models/rubraAI/Meta-Llama-3-8B-Instruct) | 8,000 | 8B | Meta | +| [rubra-ai/Meta-Llama-3-70B-Instruct](https://www.modelscope.cn/models/rubraAI/Meta-Llama-3-70B-Instruct) | 8,000 | 70B | Meta | +| [rubra-ai/gemma-1.1-2b-it](https://www.modelscope.cn/models/rubraAI/Gemma-1.1-2b-Instruct) | 8,192 | 2B | Google | +| [rubra-ai/Mistral-7B-Instruct-v0.3](https://www.modelscope.cn/models/rubraAI/Mistral-7B-Instruct-v0.3) | 32,000 | 7B | Mistral | +| [rubra-ai/Mistral-7B-Instruct-v0.2](https://www.modelscope.cn/models/rubraAI/Mistral-7B-Instruct-v0.2) | 32,000 | 7B | Mistral | +| [rubra-ai/Phi-3-vision-128k-instruct](https://www.modelscope.cn/models/rubraAI/Phi-3-mini-128k-instruct)| 128,000 | 3B | Microsoft | +| [rubra-ai/Qwen2-7B-Instruct](https://www.modelscope.cn/models/rubraAI/Qwen2-7B-Instruct) | 131,072 | 7B | Qwen | ## Demo