added model

README.md

@@ -1,3 +1,103 @@
 ---
+language:
+- en
+- zh
+- ms
+- ta
+datasets:
+- billcai/ospc-dataset-v2
+tags:
+- multilingual
+- mistral
+- sft
+- chat
+- instruction
+- gptq
+widget:
+- text: "Hello World"
+  example_title: "Sample prompt"
 license: apache-2.0
+base_model: openchat/openchat-3.5-0106
 ---
+
+This model achieved 0.7600 AUROC for the [Online Safety Prize Challenge](https://ospc.aisingapore.org/) organized by AI Singapore. It is fine-tuned from [Openchat model](https://huggingface.co/openchat/openchat-3.5-0106). Note, this model is already quantized to 4-bit GPTQ.
+
+## Training details
+This model is trained on a synthetic dataset generated by Apache 2.0 licensed LLMs (Mistral and Mixtral).
+
+## How to use
+
+You can either use it to classify text or text + extracted visual description.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda"
+
+model = AutoModelForCausalLM.from_pretrained(
+    'billcai/openchat-model-ospc',
+    torch_dtype="auto",
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained('billcai/openchat-model-ospc')
+
+promptText = "<the prompt to be tested>"
+# promptText = "Image: <image caption>, Caption: <text within image>"
+
+prompt = """Check if there is unsafe content in the following message. Unsafe content is defined in the following categories.
+    <BEGIN UNSAFE CONTENT CATEGORIES>
+    Contains hate speech and harmful content. Harmful content centres on divisive and contentious subject matters. Typical areas include:
+    - Racial disparities
+    - Religious beliefs and practices
+    - Sexual orientation
+    - Nationalistic sentiments and xenophobia against migrants
+    - Socio-economic divides and class struggles
+    - Age-related biases
+    - Gender discrimination
+    - Discrimination based on illnesses and disabilities
+    These content may be based on Singapore context, including the use of non-English languages like Mandarin, Malay and Tamil.
+    <END UNSAFE CONTENT CATEGORIES>
+
+    This is the message you are checking if it contains unsafe content.
+    <BEGIN MESSAGE>
+    {}
+    <END MESSAGE>
+
+    Provide your safety assessment for the message above. Your first line MUST read 'safe' or 'unsafe'.
+    """.format(
+            promptText
+        )
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant deciding whether a piece of content is safe or unsafe based on specific criteria. The content may contain irrelevant words as it has been extracted from an image."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to('cuda')
+generation_output = llm.generate(
+    model_inputs.input_ids,
+    max_new_tokens=10,
+    temperature=0.1,
+    output_logits=True,
+    return_dict_in_generate=True
+)
+generated_sequences = generation_output['sequences']
+generated_logits = generation_output['logits']
+unsafeTokenId = tokenizer.encode('unsafe')[1]
+safeTokenId = tokenizer.encode('safe')[1]
+firstLogit = generated_logits[0].cpu().numpy()
+prob = softmax([
+    firstLogit[0,unsafeTokenId],
+    firstLogit[0,safeTokenId],
+    ])
+print(prob) # first is score for unsafe token.
+```
+
+# License
+
+Apache 2.0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/home/tars/memes/memes2024/openchat-3.5-0106",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.1,
+    "dataset": "c4-new",
+    "desc_act": false,
+    "group_size": 128,
+    "modules_in_block_to_quantize": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "true_sequential": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "max_length": 8192,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ae2e57f096c5d7fe8d5c0be87e4202032509fa628f96be7e7f45bd7ef9bbdb
+size 4795352944

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 8192,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}