Upload 10 files

Initial draft commit

README.md

@@ -1,3 +1,34 @@
 ---
 license: gpl-3.0
----
+language:
+  - ta
+inference:
+  parameters:
+    max_new_tokens: 250
+    repetition_penalty: 1.4
+    do_sample: True
+    temperature: 0.01  # Added to match the script's generation behavior
+widget:
+  - text: |
+      இன்னாமை வேண்டின்
+    example_title: "Venba 1"
+  - text: |
+      பாடல்:
+      நின்றன நின்றன நில்லாகும்
+    example_title: "Venba 2"
+  - text: |
+      பாடல்:
+      துகள்தீர் பெருஞ்செல்வம்
+    example_title: "Venba 3"
+  - text: |
+      பாடல்:
+      கொங்குதேர் வாழ்க்கை அஞ்சிறைத் தும்பி
+    example_title: "Venba 4"
+  - text: |
+      பாடல்:
+      செல்வத்துட் செல்வம்
+    example_title: "Venba 5"
+  - text: |
+      வேதம் உரைத்தானும் வேதிய னாகிலன்
+    example_title: "Venba 6"
+---

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "marabutamil_60M",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 2.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.1",
+  "use_cache": false,
+  "vocab_size": 16000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.37.1",
+  "use_cache": false
+}

infer.py

@@ -0,0 +1,13 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("./")
+model = AutoModelForCausalLM.from_pretrained("./")
+#prompt = f"""பாடல்:
+#நின்றன நின்றன நில்லா"""
+prompt = f"""இன்னாமை வேண்டின்"""
+input_ids = tokenizer(prompt, return_tensors="pt").input_ids
+
+generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=256, repetition_penalty=1.4, temperature=0.01, do_sample=False
+)
+print(tokenizer.decode(generation_output[0]))

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f6dd3a7503c06bf0b1c2ddd5ebefc882dc205c157d46038bb476f521a14634
+size 233392032

requirements.txt

@@ -0,0 +1 @@
+transformers==4.37.1

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35aa85f6a206e8778db8de1066b107153476a4c079ef7e8e8a8b121991090fc0
+size 651581

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}