feat(model): add Hugging Face Hub publication support

- Add config.json with full model architecture specifications
- Enhance README.md with HF model card metadata:
- Add license (Apache 2.0)
- Include model-index with performance metrics
- Add standardized tags for discoverability
- Prepare for model publication via huggingface_hub API

This commit prepares the model for publication on the Hugging Face Hub by:
1. Providing necessary configuration files
2. Adding required metadata for model cards
3. Documenting performance characteristics in standard format

README.md

@@ -1,5 +1,25 @@
 # Shoonya v0.1 - Lightweight CPU-Friendly Language Model
 
+---
+language:
+- en
+license: apache-2.0
+library_name: custom
+tags:
+- cpu-inference
+- lightweight
+- text-generation
+model-index:
+- name: Shoonya
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - type: throughput
+      value: "100ms/inference"
+      name: CPU Inference Speed
+---
+
 ## Model Description
 Shoonya is a lightweight transformer-based language model designed specifically for CPU inference. Built with efficiency in mind, it features a compact architecture while maintaining coherent text generation capabilities.
 

config.json

@@ -0,0 +1,12 @@
+{
+  "architectures": ["TransformerLM"],
+  "model_type": "transformer",
+  "n_layer": 4,
+  "n_head": 4,
+  "n_embd": 128,
+  "vocab_size": 50257,
+  "max_position_embeddings": 128,
+  "intermediate_size": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0"
+}

shoonya_model_v0_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0559892e5f04adf325ccb914bfaa015ce61b1900e43cbb748c466eb1d224726d
+size 53675947

shoonya_model_v0_1_quantized.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5588d58368becbd22837a24806cf30e0f77a9a989f1e114cbfb1f6e03bdf2642
+size 32824339