Duplicate from yodi/karina

Co-authored-by: yodi <yodi@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,181 @@
+---
+datasets:
+- Local
+license: bigscience-bloom-rail-1.0
+language:
+- id
+pipeline_tag: text-generation
+duplicated_from: yodi/karina
+---
+
+#  Table of Contents
+
+1. [Model Summary](#model-summary)
+2. [Use](#use)
+4. [Training](#training)
+
+# Model Summary
+
+> We present KARINA, finetuned from BLOOMZ bigscience/bloomz-3b, a family of models capable of following human instructions in dozens of languages zero-shot. We finetune BLOOMZ pretrained multilingual language models on our crosslingual task mixture (xP3) and find the resulting models capable of crosslingual generalization to unseen tasks & languages.
+
+# Use
+
+## Intended use
+
+We recommend using the model to perform tasks expressed in natural language. For example, given the prompt "*prompt = f"Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n"*", the model will most likely answer "*Saya Karina. Ada yang bisa saya bantu?*".
+
+## How to use
+
+### CPU
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install -q transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+MODEL_NAME = "yodi/karina"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+inputs = tokenizer.encode("Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n", return_tensors="pt")
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))
+```
+
+</details>
+
+### GPU in 4 bit
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install -q transformers 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+
+MODEL_NAME = "yodi/karina"
+
+model_4bit = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="cuda:1", load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+prompt = f"Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n"
+
+generator = pipeline('text-generation',
+                     model=model_4bit,
+                     tokenizer=tokenizer,
+                     do_sample=False)
+
+result = generator(prompt, max_length=256)
+print(result)
+
+```
+
+</details>
+
+### GPU in 8bit
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+# pip install -q transformers 
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+
+MODEL_NAME = "yodi/karina"
+
+model_4bit = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="cuda:1", load_in_8bit=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+prompt = f"Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n"
+
+generator = pipeline('text-generation',
+                     model=model_4bit,
+                     tokenizer=tokenizer,
+                     do_sample=False)
+
+result = generator(prompt, max_length=256)
+print(result)
+```
+
+</details>
+
+```
+[{'generated_text': 'Given the question:\n{ siapa kamu? }\n---\nAnswer:\nSaya Karina, asisten virtual siap membantu seputar estimasi harga atau pertanyaan lain'}]
+```
+
+### Infer in Local with Gradio 
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+import re
+
+import gradio as gr
+
+MODEL_NAME = "yodi/karina"
+
+model_4bit = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="cuda:1", load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+prompt = f"Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n"
+
+generator = pipeline('text-generation',
+                     model=model_4bit,
+                     tokenizer=tokenizer,
+                     do_sample=False)
+
+def preprocess(text):
+    return f"Given the question:\n{{ {text} }}\n---\nAnswer:\n"
+
+def generate(text):
+    preprocess_result = preprocess(text)
+    result = generator(preprocess_result, max_length=256)
+    output = re.split(r'\Given the question:|Answer:|Answer #|Title:',result[0]['generated_text'])[2]
+
+    return output
+
+with gr.Blocks() as demo:
+    input_text = gr.Textbox(label="Input", lines=1)
+    button = gr.Button("Submit")
+    output_text = gr.Textbox(lines=6, label="Output")
+    button.click(generate, inputs=[input_text], outputs=output_text)
+
+demo.launch(enable_queue=True, debug=True)
+```
+And open the gradio url from browser.
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+- PEFT 0.5.0.dev0
+
+<!-- Necessary for whitespace -->
+###
+
+# Limitations
+
+**Prompt Engineering:** The performance may vary depending on the prompt and its following BLOOMZ models.
+
+# Training
+
+## Model
+
+- **Architecture:** Same as [bloom](https://huggingface.co/bigscience/bloom), also refer to the `config.json` file

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloomz-3b",
+  "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": 2560,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "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": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9396aa5934350d8ae5a95c7d043a7e3d3396e4b8eaf8301b8cda55929faad2d4
+size 6005240157

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 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}