Upload trained model

MODEL_CARD.md

@@ -0,0 +1,9 @@
+# GPT4All-Model (Hanuman)
+
+Model card placeholder. Provide details here: training data, license, evaluation, intended use, limitations.
+
+- Name: GPT4All-Model
+- Architecture: Hanuman (custom)
+- Vocab size: see `config.json`
+- License: add LICENSE file in repo root
+

README.md

@@ -0,0 +1,55 @@
+# GPT4All-Model (Hanuman)
+
+This folder contains the files needed to load and run the custom Hanuman model.
+
+Included files:
+
+- `pytorch_model.bin` — model weights
+- `config.json` — model configuration
+- `tokenizer.json`, `tokenizer_config.json`, `special_tokens_map.json` — tokenizer files
+- `modeling.py` — custom `Hanuman` model implementation
+- `hanuman_loader.py` — convenience loader (optional)
+
+Quick usage (local files in this folder):
+
+```python
+# inference_local.py
+from transformers import AutoTokenizer
+from modeling import Hanuman
+import torch
+
+# load tokenizer from local folder
+tokenizer = AutoTokenizer.from_pretrained('.')
+# load model using the provided helper
+model = Hanuman.from_pretrained('.', map_location='cpu')
+
+prompt = "สวัสดีครับ ช่วยอธิบายสั้น ๆ เกี่ยวกับประเทศไทย"
+inputs = tokenizer(prompt, return_tensors='pt')
+outputs = model.generate(inputs['input_ids'], max_new_tokens=50, temperature=1.2, top_k=50, top_p=0.95)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+Or load from the Hugging Face Hub (if this folder was uploaded to the hub as the repo root):
+
+```python
+# inference_from_hub.py
+from transformers import AutoTokenizer
+from hanuman_loader import HanumanModel
+
+repo_id = "ZombitX64/GPT4All-Model"
+# tokenizer will download from HF
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+# HanumanModel downloads weights and modeling.py dynamically
+model_wrapper = HanumanModel.from_pretrained(repo_id, map_location='cpu')
+model = model_wrapper.model
+
+prompt = "สวัสดีครับ ช่วยสรุปประเทศไทยสั้น ๆ"
+inputs = tokenizer(prompt, return_tensors='pt')
+outputs = model.generate(inputs['input_ids'], max_new_tokens=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+Notes:
+- This repo uses a custom model class (`Hanuman`) — users must keep `modeling.py` or use the provided `hanuman_loader.py` that dynamically imports it.
+- For CPU inference, install a CPU build of PyTorch. For GPU, install the appropriate CUDA-enabled PyTorch.
+

inference_from_hub.py

@@ -0,0 +1,16 @@
+from transformers import AutoTokenizer
+from hanuman_loader import HanumanModel
+
+
+def run(prompt: str = "สวัสดีครับ ช่วยสรุปประเทศไทยสั้น ๆ"):
+    repo_id = "ZombitX64/GPT4All-Model"
+    tokenizer = AutoTokenizer.from_pretrained(repo_id)
+    model_wrapper = HanumanModel.from_pretrained(repo_id, map_location='cpu')
+    model = model_wrapper.model
+    inputs = tokenizer(prompt, return_tensors='pt')
+    out = model.generate(inputs['input_ids'], max_new_tokens=50, temperature=1.2, top_k=50, top_p=0.95)
+    print(tokenizer.decode(out[0], skip_special_tokens=True))
+
+
+if __name__ == '__main__':
+    run()

inference_local.py

@@ -0,0 +1,15 @@
+from transformers import AutoTokenizer
+from modeling import Hanuman
+import torch
+
+
+def run(prompt: str = "สวัสดี"): 
+    tokenizer = AutoTokenizer.from_pretrained('.')
+    model = Hanuman.from_pretrained('.', map_location='cpu')
+    inputs = tokenizer(prompt, return_tensors='pt')
+    out = model.generate(inputs['input_ids'], max_new_tokens=50, temperature=1.2, top_k=50, top_p=0.95)
+    print(tokenizer.decode(out[0], skip_special_tokens=True))
+
+
+if __name__ == '__main__':
+    run("สวัสดีครับ ช่วยอธิบายประเทศไทยสั้น ๆ")

pytorch_model copy.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56adef99dca3dbd97fe7df9deebe94df1525e7fa290dc7a211c0d37abbeb430
+size 241866511

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+huggingface_hub
+safetensors