Make creation examples standalone with public dependencies

.meta.json

@@ -8,7 +8,6 @@
   "numpy": "2.3.5",
   "safetensors": "0.8.0",
   "sglang": "0.5.23.dev384+g9ab74b851",
-  "tiny-random": "0.2.0",
   "torch": "2.14.1",
   "torchcodec": "0.17.0",
   "transformers": "5.19.0",

README.md

@@ -104,13 +104,15 @@ print(processor.decode(output[0, inputs['input_ids'].shape[1]:], skip_special_to
 
 ```python
 import json
+from copy import deepcopy
 from pathlib import Path
+from shutil import copyfile
 
 import torch
-from huggingface_hub import hf_hub_download
+from huggingface_hub import hf_hub_download, list_repo_files
+from safetensors.torch import save_file
 from transformers import AutoConfig, AutoModelForImageTextToText, set_seed
-# Creation helpers: pip install git+https://github.com/yujiepan/tiny-random.git
-from tiny_random.qwen_utils import add_qwen4_mtp, copy_qwen_source_assets, save_random_qwen_checkpoint
+from transformers.models.qwen4_exp.modeling_qwen4_exp import Qwen4ExpTextRMSNorm
 
 source_model_id = "Qwen/Qwen3.8-Flash-Next"
 save_folder = "/tmp/tiny-random/qwen38-flash-next"
@@ -132,9 +134,50 @@ raw['vision_config'].update(depth=2, hidden_size=64, intermediate_size=128, num_
 (folder / 'config.json').write_text(json.dumps(raw, indent=2))
 config = AutoConfig.from_pretrained(folder)
 model = AutoModelForImageTextToText.from_config(config, dtype=torch.bfloat16)
-add_qwen4_mtp(model, model.model.language_model)
-save_random_qwen_checkpoint(model, folder)
-copy_qwen_source_assets(source_model_id, source_revision, folder)
+backbone = model.model.language_model
+text = backbone.config
+width = text.hidden_size
+model.mtp = torch.nn.ModuleDict({
+    "fc_embedding": torch.nn.Linear(width, width, bias=False, dtype=torch.bfloat16),
+    "fc_hidden": torch.nn.Linear(width, width, bias=False, dtype=torch.bfloat16),
+    "pre_fc_norm_embedding": Qwen4ExpTextRMSNorm(width, eps=text.rms_norm_eps).to(torch.bfloat16),
+    "pre_fc_norm_hidden": Qwen4ExpTextRMSNorm(width * text.hc_count, eps=text.rms_norm_eps).to(torch.bfloat16),
+    "layers": torch.nn.ModuleList([deepcopy(backbone.layers[-1])]),
+    "hyper_connection_mixer": deepcopy(backbone.hyper_connection_mixer),
+})
+with torch.no_grad():
+    for name, param in sorted(model.named_parameters()):
+        if name.endswith("A_log"):
+            param.zero_()
+        elif name.endswith("dt_bias"):
+            param.fill_(1)
+        elif "norm" in name and name.endswith("weight"):
+            param.fill_(1 if "visual" in name or ".linear_attn.norm." in name else 0)
+        elif name.endswith("bias"):
+            param.zero_()
+        else:
+            torch.nn.init.normal_(param, mean=0, std=0.02)
+state = {name: value.detach().cpu().contiguous() for name, value in model.state_dict().items()}
+# The public checkpoint stores PLE embeddings in shard_N tensors.
+for name in list(state):
+    if not name.endswith(".ple.ple_embedding.ngram_embedding.weight"):
+        continue
+    table = state.pop(name)
+    parts = text.split_ngram_parts
+    rows = (table.shape[0] + parts - 1) // parts
+    prefix = name.removesuffix(".weight")
+    for part in range(parts):
+        state[f"{prefix}.shard_{part}.weight"] = table[part * rows:(part + 1) * rows].contiguous()
+save_file(state, folder / "model.safetensors", metadata={"format": "pt"})
+# Preserve tokenizer, processor and generation assets exactly as published.
+assets = {
+    "tokenizer.json", "tokenizer_config.json", "special_tokens_map.json",
+    "vocab.json", "merges.txt", "added_tokens.json", "chat_template.jinja",
+    "chat_template.json", "preprocessor_config.json", "processor_config.json",
+    "video_preprocessor_config.json", "generation_config.json",
+}
+for name in sorted(set(list_repo_files(source_model_id, revision=source_revision)) & assets):
+    copyfile(hf_hub_download(source_model_id, name, revision=source_revision), folder / name)
 ```
 
 </details>
@@ -160,7 +203,6 @@ Qwen3.8 Flash-Next: 8 backbone layers + 1 HC-aware MTP layer; hidden_size=4
 - numpy: 2.3.5
 - safetensors: 0.8.0
 - sglang: 0.5.23.dev384+g9ab74b851
-- tiny-random: 0.2.0
 - torch: 2.14.1
 - torchcodec: 0.17.0
 - transformers: 5.19.0
@@ -171,5 +213,6 @@ Qwen3.8 Flash-Next: 8 backbone layers + 1 HC-aware MTP layer; hidden_size=4
 ### Change log:
 
 - 2026-10-23: Initial version.
+- 2026-10-23: Creation examples use only public dependencies; source assets are copied unchanged.
 
 This repo is generated by GPT-6.1-Sol