Upload README.md with huggingface_hub

README.md

@@ -39,6 +39,7 @@ Q4NX is FastFlowLM's native packed-quantization format - a rearranged Q4_1 layou
 | tokenizer.json | Tokenizer |
 | tokenizer_config.json | Special tokens and chat template |
 | chat_template.jinja | Chat template (optional) |
+| README.md | |
 | flm-add.py | Installer script - registers this model with FastFlowLM |
 
 ## Install and run
@@ -53,8 +54,8 @@ export FLM_CONFIG_PATH="$HOME/.config/flm/model_list.json"
 export FLM_XCLBIN_PATH="$HOME/.config/flm"
 
 git lfs install
-git clone https://huggingface.co/Atomic-Germ/Orinth-1.0-35B-NPU2
-cd Orinth-1.0-35B-NPU2
+git clone https://huggingface.co/Atomic-Germ/Ornith-1.0-35B-NPU2
+cd Ornith-1.0-35B-NPU2
 python3 ./flm-add.py .
 flm run qwen3.6-moe:35b-a3b
 ```
@@ -63,14 +64,14 @@ Run `python3 ./flm-add.py --help` for all options. Without a clone, the same
 command works against the repo id directly:
 
 ```bash
-python3 ./flm-add.py Atomic-Germ/Orinth-1.0-35B-NPU2
+python3 ./flm-add.py Atomic-Germ/Ornith-1.0-35B-NPU2
 ```
 
 If the model has not been published yet, deploy the local directory with the
 converter instead:
 
 ```bash
-python convert.py -i <source.gguf> -o <this directory> -d qwen3.6-moe:35b-a3b --deploy-name "Orinth-1.0-35B-NPU2"
+python convert.py -i <source.gguf> -o <this directory> -d qwen3.6-moe:35b-a3b --deploy-name "Ornith-1.0-35B-NPU2"
 ```
 
 ## Kernels
@@ -97,6 +98,7 @@ curl http://127.0.0.1:8080/v1/chat/completions \
 - Context length: 262,144 tokens (from config)
 - Hidden size: 2048
 - Layers: 40
+- Intermediate size: 512
 - Vocabulary: 248320
 - `model.q4nx` size: 21.64 GB
 - Base model: [ornith-ai/Ornith-1.0-35B](https://huggingface.co/ornith-ai/Ornith-1.0-35B)