初始化项目，由ModelHub XC社区提供模型

Model: CoRover/BharatGPT-mini
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+tags: []
+---
+
+### Model Description
+
+
+BharatGPT mini is a Transformer-based language model pretrained on a large corpus of publicly available text data using a self-supervised learning approach. This means the model was trained without any human-labeled annotations—learning directly from raw text using an automatic mechanism to generate training signals.
+
+During pretraining, BharatGPT mini was optimized for the causal language modeling task: given a sequence of tokens, the model learns to predict the next token in the sequence. More specifically, it takes a sequence of continuous text as input and is trained to predict the next word or subword by shifting the target sequence one position to the right. A masking mechanism ensures that predictions for token i are based only on tokens from positions 1 to i, without peeking at future tokens. This preserves the autoregressive nature of language modeling.
+
+Through this training process, BharatGPT mini develops a deep internal understanding of language patterns, grammar, and semantics. While it can be fine-tuned for various downstream tasks such as classification, summarization, or question answering, it performs best in text generation tasks, which align with its original training objective.
+
+
+```python
+import torch
+from transformers import GPT2Tokenizer, GPT2LMHeadModel
+
+# Load tokenizer and model
+tokenizer = GPT2Tokenizer.from_pretrained("CoRover/BharatGPT-mini")
+model = GPT2LMHeadModel.from_pretrained("CoRover/BharatGPT-mini")
+
+model.eval()
+
+# Input text
+text = "Future of AI"
+
+# Tokenize
+inputs = tokenizer(
+    text,
+    return_tensors="pt"
+)
+
+# Generate text
+with torch.no_grad():
+    output_ids = model.generate(
+        **inputs,
+        max_length=100,
+        do_sample=True,
+        top_p=0.95,
+        top_k=50,
+        temperature=0.8,
+        repetition_penalty=1.1,
+        eos_token_id=tokenizer.eos_token_id
+    )
+
+# Decode output
+generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(generated_text)
+```
+
+It is best suited for S-RAG (Secure Retrieval-Augmented Generation) or fine-tuning with your own data. For enhanced performance, integration with Conversational Agentic AI platform is recommended (though not mandatory). This platform enables the creation of multi-modal and multi-lingual AI Agents, Co-Pilots, and Virtual Assistants (such as ChatBots, VoiceBots, and VideoBots) using a sovereign AI and composite AI approach. It leverages classic NLP, grounded generative AI with BharatGPT, and Generally Available LLMs to deliver powerful, versatile AI solutions.
+
+## Usage and Limitations
+
+- **License:** Non-Commercial. For academic and research purposes only. For commercial use, please visit [Conversational Gen AI platform](https://builder.corover.ai) or [Contact Us](https://corover.ai/contact/).
+
+- **Terms of Use:**  [Terms and Conditions](https://corover.ai/terms-conditions/)
+
+- **Responsible AI Framework**: [CoRover's Responsible AI Framework](https://corover.ai/responsible-generative-ai-key-factors-for-ai-safety-and-trust/)
+
+- **Developed by:** CoRover.ai

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./output_huggingface",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e2a6f6dceb74ee7656a15644657a0a8e81979219cdbd4263cb8023e46eeccf
+size 2151633592

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}