Upload 6 files

.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

app.py

@@ -0,0 +1,92 @@
+from transformers import (
+    AutoModelForSequenceClassification, 
+    AutoTokenizer, 
+    TrainingArguments, 
+    Trainer
+)
+from datasets import load_dataset
+import torch
+
+# 1. Load dataset
+dataset = load_dataset("zxc4wewewe/offsec")
+
+# 2. Add labels (required for classification)
+# Modify based on your actual classification task:
+def add_labels(example):
+    # Example: Classify if prompt is malicious (1) or benign (0)
+    # Replace this logic with your actual labels!
+    malicious_keywords = ['hack', 'exploit', 'crack', 'bypass', 'inject']
+    text_lower = example["prompt"].lower()
+    example["labels"] = 1 if any(kw in text_lower for kw in malicious_keywords) else 0
+    return example
+
+dataset = dataset.map(add_labels)
+
+# 3. Load Tokenizer
+tokenizer = AutoTokenizer.from_pretrained("zxc4wewewe/blackthinking")
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+# 4. Tokenize dataset
+def tokenize_function(batch):
+    tokenized = tokenizer(
+        batch["prompt"], 
+        padding=True, 
+        truncation=True, 
+        max_length=512
+    )
+    tokenized["labels"] = batch["labels"]
+    return tokenized
+
+dataset = dataset.map(tokenize_function, batched=True)
+dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
+
+# 5. Load Model with SafeTensors support
+model = AutoModelForSequenceClassification.from_pretrained(
+    "zxc4wewewe/blackthinking",
+    num_labels=2,
+    torch_dtype=torch.float16,  # Optional: saves memory
+    use_safetensors=True        # Force SafeTensors loading
+)
+
+# 6. Training Arguments with SafeTensors saving
+training_args = TrainingArguments(
+    output_dir="./safetensors_results",
+    num_train_epochs=3,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=2,
+    learning_rate=2e-5,
+    logging_steps=10,
+    save_strategy="epoch",
+    
+    # SafeTensors Configuration
+    save_safetensors=True,      # Save as .safetensors (not .bin)
+    load_best_model_at_end=True,
+    
+    # Optional optimizations
+    fp16=torch.cuda.is_available(),  # Use FP16 if GPU available
+    report_to="none"
+)
+
+# 7. Initialize Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=dataset["train"].shuffle(seed=42).select(range(1000)),
+    eval_dataset=dataset["test"].shuffle(seed=42).select(range(200)) if "test" in dataset else None,
+    tokenizer=tokenizer,
+)
+
+# 8. Train and Save
+print("Starting training with SafeTensors format...")
+trainer.train()
+
+# Save final model in SafeTensors format
+trainer.save_model("./final_safetensors_model")
+print("Model saved in SafeTensors format!")
+
+# 9. Verification - Check files
+import os
+model_path = "./final_safetensors_model"
+files = os.listdir(model_path)
+print("Saved files:", [f for f in files if f.endswith(('.safetensors', '.json', '.txt'))])

config.json

@@ -1,16 +1,13 @@
 {
-  "_name_or_path": "unsloth/meta-llama-3.1-8b-instruct",
+  "_name_or_path": "meta-llama/meta-Llama-3.1-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": [
-    128001,
-    128008,
-    128009
-  ],
+  "eos_token_id": 128009,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -23,6 +20,26 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -34,8 +51,8 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.0.dev0",
-  "unsloth_version": "2024.8",
+  "transformers_version": "4.49.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -10,5 +10,5 @@
   "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.0.dev0"
+  "transformers_version": "4.49.0.dev0"
 }

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_bos_token": true,
   "added_tokens_decoder": {
     "128000": {
       "content": "<|begin_of_text|>",
@@ -2053,12 +2054,14 @@
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "right",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
 }