Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+library_name: pytorch
+tags: [tool-calling, agent, tiny-llm, byte-level, on-device, from-scratch]
+pipeline_tag: text-generation
+---
+
+# tiny-30m-byte — LocalAgent (28.32M params)
+
+A **from-scratch, byte-level** tool-calling agent model from
+[LocalAgent](https://github.com/sangbumchoi/localagent). Pure PyTorch, **28.32M params**,
+trained on CPU. It pairs a tiny decoder (GQA + RoPE + SwiGLU) with a **dual head**
+(tool-selection classifier + pointer/copy argument head) and **prompt-grounded constrained
+decoding** for reliable tool calls across 21 tools (general assistant, the Claude Code /
+Codex coding surface, and computer-use / productivity tools), including parallel two-call turns.
+
+## Architecture
+- vocab 256 (byte-level), d_model 512, layers 10, heads 8/2 (GQA), ffn 1408
+- factorized embeddings: False
+
+## Files
+- `config.json` — `ModelConfig`
+- `model.safetensors` / `pytorch_model.bin` — decoder weights
+- `agent_heads.bin` — trained tool-selection + pointer heads (optional)
+
+## What it can do (use cases)
+One byte-level model that turns a natural-language turn into a grounded tool call — across an
+assistant, a coding agent, computer-use/productivity apps, and **parallel two-call** turns:
+
+| you say | it calls |
+|---|---|
+| "What's the weather in Cusco?" | `get_weather(city="Cusco")` |
+| "What is 19 * 19 * 5?" | `calculator(expression="19*19*5")` |
+| "Open the file bin/run.sh." | `read_file(path="bin/run.sh")` |
+| "Grep for 'TODO'." | `grep_search(pattern="TODO")` |
+| "Run the tests." | `run_tests()` |
+| "Commit with message 'fix bug'." | `git_commit(message="fix bug")` |
+| "Send an email to Greta." | `send_email(recipient="Greta")` |
+| "Go to figma.com." | `open_url(url="figma.com")` |
+| "Send a Slack message saying 'ship it'." | `slack_send(message="ship it")` |
+| "Create a Jira ticket titled 'broken link'." | `jira_issue(summary="broken link")` |
+| "Compose an email to Judy **and** search for how tall is Everest." | `send_email(recipient="Judy")` + `web_search(query="how tall is Everest")` |
+
+Multi-turn coding (grounds a follow-up arg from a tool response):
+`read_file(tests/test_api.py)` → result → `run_tests()` → "FAILED…" → fix.
+At catalog scale (100s–1000s of tools) selection is done by **retrieval** (top-k) instead of a
+fixed head. See the [LocalAgent repo](https://github.com/sangbumchoi/localagent).
+
+## Load (pure PyTorch, no transformers)
+```python
+import json, torch
+from huggingface_hub import hf_hub_download
+from localagent.model import LocalAgentLM, ModelConfig
+
+cfg_d = json.load(open(hf_hub_download("danelcsb/localagent-tiny-30m-byte", "config.json")))
+cfg = ModelConfig(**{k: v for k, v in cfg_d.items() if k in ModelConfig.__dataclass_fields__})
+model = LocalAgentLM(cfg)
+from safetensors.torch import load_file
+model.load_state_dict(load_file(hf_hub_download("danelcsb/localagent-tiny-30m-byte", "model.safetensors")))
+model.eval()
+```
+See the LocalAgent repo for the grounded decoder / agent runtime (tool head, pointer head,
+retrieval, parallel-call decode).

agent_heads.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff11474f1e307741d924d6b3bda02903813d5a9d14652e450fbab8b1e8bbd5b
+size 2179973

config.json

@@ -0,0 +1,18 @@
+{
+  "model_type": "localagent",
+  "architecture": "LocalAgentLM (byte-level GQA+RoPE+SwiGLU)",
+  "name": "tiny-30m-byte",
+  "vocab_size": 256,
+  "d_model": 512,
+  "embed_dim": 512,
+  "n_layers": 10,
+  "n_loops": 1,
+  "n_heads": 8,
+  "n_kv_heads": 2,
+  "ffn_hidden": 1408,
+  "max_seq_len": 1024,
+  "rope_theta": 10000.0,
+  "norm_eps": 1e-05,
+  "tie_embeddings": true,
+  "dropout": 0.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40080f461c6c061150674f5dae2bf0079d2eb2d0812da4e503de0be4dc7af982
+size 113297896