Upload Hindi CausalLM model

README.md

@@ -0,0 +1,53 @@
+---
+language:
+- hi
+tags:
+- hindi
+- text-generation
+- causal-lm
+- lm
+license: mit
+datasets:
+- custom_hindi_corpus
+---
+
+# Hindi-CausalLM
+
+A Hindi language generation model with the following specifications:
+
+## Model Architecture
+- **Type**: Causal Language Model with Transformer architecture
+- **Hidden size**: 768
+- **Layers**: 12
+- **Attention heads**: 16
+- **Key-value heads**: 4 (using grouped-query attention)
+- **Vocabulary size**: 16000
+- **Parameters**: ~74.1M
+- **Context window**: 512 tokens
+- **Trained on**: Large corpus of Hindi text
+
+## Training
+
+The model was trained on a large corpus of Hindi text using a cosine learning rate schedule with warmup. Training utilized mixed-precision and distributed data parallel across multiple GPUs.
+
+## Capabilities
+
+This model can:
+- Generate coherent Hindi text
+- Continue text from a given prompt
+- Create stories, explanations, and other content in Hindi
+
+## Limitations
+
+- Performance varies based on the similarity of the input to the training data
+- May occasionally generate repetitive content for longer texts
+- May produce grammatically incorrect Hindi in some contexts
+- Has no knowledge of events beyond its training corpus
+
+## Intended Use
+
+This model is intended for Hindi language generation tasks, creative writing assistance, and as a foundation for fine-tuning on specific tasks.
+
+## Ethical Considerations
+
+Users should be aware that like all language models, this model may reproduce biases or generate problematic content in certain contexts.

config.json

@@ -0,0 +1,73 @@
+{
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": null,
+  "pad_token_id": null,
+  "eos_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null,
+  "_name_or_path": "",
+  "_attn_implementation_autoset": true,
+  "transformers_version": "4.51.1",
+  "vocab_size": 16000,
+  "hidden_size": 768,
+  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 4,
+  "intermediate_size": 3072,
+  "hidden_act": "silu",
+  "max_position_embeddings": 512,
+  "model_type": "convaicausallm"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b013bef88c7f7cbf72bd25d7868854da142b00a899adc94175294b50a04d4dd
+size 408609208

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57c2ac93848af94c4dcbb2f93a6406135c030a2e0c9b717588f4f5929b13551
+size 408661966

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1658727f4ea5c571f69a60f6defcd180014a1d69be6e9c1ec360d9510aa6b5e
+size 642200