Upload README.md with huggingface_hub

README.md

@@ -1,53 +1,60 @@
 ---
-library_name: transformers
+library_name: llama.cpp
 license: apache-2.0
-pipeline_tag: text-generation
+pipeline_tag: image-text-to-text
+base_model: InternScience/Agents-A1
 tags:
+- gguf
 - llama-cpp
-- gguf-my-repo
-base_model: InternScience/Agents-A1
+- multimodal
+- vision
+- moe
+- agentic
 ---
 
-# alexop1000/Agents-A1-Q8_0-GGUF
-This model was converted to GGUF format from [`InternScience/Agents-A1`](https://huggingface.co/InternScience/Agents-A1) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-Refer to the [original model card](https://huggingface.co/InternScience/Agents-A1) for more details on the model.
+# Agents-A1 — Q8_0 GGUF (with vision)
 
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+GGUF quantization of [`InternScience/Agents-A1`](https://huggingface.co/InternScience/Agents-A1) for [llama.cpp](https://github.com/ggml-org/llama.cpp), **including the vision projector** so the model keeps its multimodal (image + text) capability.
 
-```bash
-brew install llama.cpp
+| File | Type | Size | Notes |
+|------|------|------|-------|
+| `agents-a1-q8_0.gguf` | text model, **Q8_0** | 36.9 GB | chat template + tokenizer embedded |
+| `mmproj-Agents-A1-f16.gguf` | vision projector, **F16** | 0.9 GB | required for image input |
+| `chat_template.jinja` | chat template | — | already baked into the GGUF; loose copy for `--chat-template-file` overrides |
 
-```
-Invoke the llama.cpp server or the CLI.
+Converted with `llama.cpp/convert_hf_to_gguf.py` (architecture `qwen35moe`, registered upstream as `Qwen3_5MoeForConditionalGeneration`). The chat template embedded in the GGUF is byte-identical to the upstream `chat_template.jinja` and includes the vision-token, tool-call, and `<think>` reasoning logic.
+
+> [!IMPORTANT]
+> Agents-A1 uses a **hybrid linear-attention + MoE** architecture (Qwen3.5-MoE family). You need a **recent llama.cpp build** that supports the `qwen35moe` inference graph — converter support landing does not guarantee your local binary can run it. If the model fails to load, update and rebuild llama.cpp from `master`.
+
+## Usage
+
+### Text + vision (recommended)
+
+Download both GGUFs, then point `--mmproj` at the projector:
 
-### CLI:
 ```bash
-llama-cli --hf-repo alexop1000/Agents-A1-Q8_0-GGUF --hf-file agents-a1-q8_0.gguf -p "The meaning to life and the universe is"
+llama-server -m agents-a1-q8_0.gguf --mmproj mmproj-Agents-A1-f16.gguf -c 8192 -ngl 99
 ```
 
-### Server:
+Then send images via the web UI or the OpenAI-compatible `image_url` message format.
+
+### Text only
+
 ```bash
-llama-server --hf-repo alexop1000/Agents-A1-Q8_0-GGUF --hf-file agents-a1-q8_0.gguf -c 2048
+llama-cli -m agents-a1-q8_0.gguf -p "Hello"
 ```
 
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+Omitting `--mmproj` runs the language model alone and frees the compute/KV the vision encoder would use.
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+---
 
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-```
-cd llama.cpp && LLAMA_CURL=1 make
-```
+## About the original model
 
-Step 3: Run inference through the main binary.
-```
-./llama-cli --hf-repo alexop1000/Agents-A1-Q8_0-GGUF --hf-file agents-a1-q8_0.gguf -p "The meaning to life and the universe is"
-```
-or
-```
-./llama-server --hf-repo alexop1000/Agents-A1-Q8_0-GGUF --hf-file agents-a1-q8_0.gguf -c 2048
-```
+**Agents-A1** is a 35B Mixture-of-Experts agentic model from [InternScience](https://huggingface.co/InternScience), built to scale heterogeneous agentic abilities across **long-horizon search, engineering, scientific research, instruction following, and tool-calling**. Despite the ~35B class, it reports competitive-to-SOTA results against much larger frontier systems on benchmarks such as Seal-0, HiPhO, FrontierScience, IFBench, BrowseComp, and GAIA.
+
+- 🏠 Homepage: https://internscience.github.io/Agents-A1/
+- 📄 Technical Report: https://arxiv.org/abs/2606.30616
+- 💻 GitHub: https://github.com/InternScience/Agents-A1
+
+See the [original model card](https://huggingface.co/InternScience/Agents-A1) for full details, benchmarks, and licensing. All credit for the model goes to InternScience; this repo only provides GGUF conversions. License: Apache-2.0.