feat: release Haste Jev 2M (Small) weights and quantized formats

README.md

@@ -0,0 +1,93 @@
+---
+language:
+- en
+library_name: transformers
+license: apache-2.0
+pipeline_tag: feature-extraction
+tags:
+- jev
+- hastejev
+- hastejev-2m
+- decision-engine
+- system-1
+- pica
+- zero-bias
+- low-latency
+- non-generative
+- autonomous-agents
+- browser-control
+- web-automation
+- agentic-ai
+- fast-inference
+- decision-making
+- calibration
+- safetensors
+- pytorch
+- quantized
+- int8
+- int4
+- fp16
+---
+
+# ⚡ Haste Jev 2M (Small) (~1.8M Parameters)
+
+[![Hugging Face Model](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-noffy%2Fhastejev-2m-yellow)](https://huggingface.co/noffy/hastejev-2m)
+[![GitHub Repository](https://img.shields.io/badge/GitHub-racstan%2Fhastejev-black?logo=github)](https://github.com/racstan/hastejev)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Parameters](https://img.shields.io/badge/Parameters-~1.8M-brightgreen.svg)]()
+[![Memory](https://img.shields.io/badge/RAM_Footprint-~7_MB-purple.svg)]()
+
+> **Haste Jev 2M (Small)** is part of the **Haste Jev** family of open-weights, zero-bias **System-1 Decision Engines**. Real-time decision kernel for autonomous browser control, robotic automation, and interactive UI agents.
+
+---
+
+## 🔬 Model Specifications
+
+- **Total Parameters**: 1,826,275 (~1.8M)
+- **Trainable Parameters**: 1,416,675
+- **Buffer / Projection Table**: 409,600
+- **Hidden Dimension ($d_{\text{model}}$)**: 160
+- **Transformer Layers**: 4
+- **Attention Heads**: 4
+- **Target Deployment**: Browser automation & bots
+- **Quantization Formats Available**: `FP32`, `FP16` (`model_fp16.safetensors`), `INT8` (`model_int8.safetensors`), `INT4` (`model_int4.safetensors`)
+
+---
+
+## ⚡ Quickstart
+
+```python
+from hastejev import HasteJevEngine
+
+# 1. Load standard weights directly from Hugging Face Hub
+engine = HasteJevEngine.from_pretrained("noffy/hastejev-2m")
+
+# 2. Or load with INT8 / INT4 quantization
+engine_int8 = HasteJevEngine.from_pretrained("noffy/hastejev-2m", quantization="int8")
+
+# 3. Execute Decision Primitives
+state = "Account balance is $14,850.50 with pending transaction of $3,200.00."
+options = ["Approve Transaction", "Flag for Review", "Decline"]
+
+res = engine.choice(state, options)
+print(f"Decision: {res.decision} (Confidence: {res.confidence:.3f})")
+```
+
+---
+
+## 📊 Complete Haste Jev Model Family
+
+| Model | Parameters | Hidden Dim | Layers | Heads | RAM (FP32) | RAM (INT8) | Target Use Case |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :--- |
+| [`hastejev-100k`](https://huggingface.co/noffy/hastejev-100k) | **~98k** | 48 | 2 | 2 | ~0.4 MB | ~0.1 MB | Microcontrollers, WASM, IoT |
+| [`hastejev-500k`](https://huggingface.co/noffy/hastejev-500k) | **~500k** | 96 | 3 | 4 | ~2.0 MB | ~0.5 MB | Mobile CPU, in-browser workers |
+| [`hastejev-1m`](https://huggingface.co/noffy/hastejev-1m) | **~1.1M** | 128 | 4 | 4 | ~4.4 MB | ~1.1 MB | High-throughput API sidecars |
+| [`hastejev-2m`](https://huggingface.co/noffy/hastejev-2m) | **~1.8M** | 160 | 4 | 4 | ~7.3 MB | ~1.8 MB | Browser automation & bots |
+| [`hastejev-5m`](https://huggingface.co/noffy/hastejev-5m) | **~5.0M** | 224 | 5 | 4 | ~20.0 MB | ~5.0 MB | Financial & KYC routing |
+| [`hastejev-10m`](https://huggingface.co/noffy/hastejev-10m) | **~10.0M** | 320 | 5 | 4 | ~40.0 MB | ~10.0 MB | Multimodal agent kernels |
+| [`hastejev-20m`](https://huggingface.co/noffy/hastejev) | **~20.4M** | 256 | 4 | 4 | ~81.5 MB | ~20.4 MB | Enterprise decision engine |
+
+---
+
+## 📄 License
+Apache License 2.0.

config.json

@@ -0,0 +1,18 @@
+{
+  "architectures": [
+    "HasteJevEngine"
+  ],
+  "model_type": "hastejev",
+  "preset_name": "2m",
+  "d_model": 160,
+  "n_layers": 4,
+  "n_heads": 4,
+  "d_ff": 640,
+  "table_size": 2560,
+  "num_frequencies": 32,
+  "vocab_size": 30522,
+  "calibrator_temperature": 1.0,
+  "torch_dtype": "float32",
+  "quantization": "int4",
+  "hastejev_version": "1.1.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfdb2a0df79592c9e82a25de036613a0e8a85eb0fb16ae11006a53aebdddd68
+size 7312956

model_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2423fcf8058c6fe17f79ae21207ff23e18dcec2de4f1d7f83a9e5e6058b861
+size 3660374

model_int4.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfdb2a0df79592c9e82a25de036613a0e8a85eb0fb16ae11006a53aebdddd68
+size 7312956

model_int8.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38a75f3b2dff1f36199ba7bbbbb538e4c675c41372b965bd29d96273889f241
+size 7312956

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35056f4474469815769464bf2813ed621e420de7eb3c652aca03f85c1631ace2
+size 7329643