Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-1b1",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3fbe6f75936af2c8e34cba603a90a790653c44f7f727119c3f8241c315f9b49
+size 4261291440

readme.md

@@ -0,0 +1,18 @@
+# Notebook Info
+**Reference**: \\
+- https://huggingface.co/docs/transformers/chat_templating \\
+- https://github.com/MicrosoftDocs/azure-docs/blob/main/articles/ai-services/openai/includes/chat-markup-language.md \\
+- https://huggingface.co/datasets/FreedomIntelligence/alpaca-gpt4-indonesian \\
+- https://huggingface.co/datasets/FreedomIntelligence/sharegpt-indonesian \\
+- https://huggingface.co/datasets/FreedomIntelligence/evol-instruct-indonesian \\
+- https://huggingface.co/datasets/jakartaresearch/indoqa \\
+
+
+**Task**: Chat or Conversational \\
+**Input**: User's prompt containing chat templated text in string format \\
+**Output**: Model's generated text in string format
+
+**Experiment**:
+- Use bos and eos token to replace <|im_start|> and <|im_end|> in ChatML. (Inspired by: https://asmirnov.xyz/doppelganger) \\
+- Penggunaan padding dan truncation sesuai max_length. \\
+- Max length = 256, karena telah mengkonsumsi 33.7 GB.

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ bos_token }}{{message['role'] + '\n' + message['content'] + '\n'}}{{ eos_token }}{% if not loop.last %}{{ '\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n'}}{{ bos_token }}{{'assistant' + '\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}