Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+base_model: microsoft/biogpt
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/biogpt",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc2",
+    "fc1",
+    "v_proj",
+    "q_proj",
+    "out_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b290344303f2e9a724feef84d639df3d0ec13bac1f4788711e41b21cdc13ba
+size 28349272

autotrain-data/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train", "validation"]}

autotrain-data/train/cache-55437dce45baf967.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96e495b96565754aed14c9376b65e955876fe3ddbf85a6e147bbb3fb7f2ed58
+size 610032

autotrain-data/train/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7326a56f21da6969d01fb2c9f15286a477dc5f0adee72d9c06dbf87eb0dd87
+size 141512

autotrain-data/train/dataset_info.json

@@ -0,0 +1,56 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "Unnamed: 0": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 1": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 2": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 5": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 6": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 7": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 8": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 9": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 10": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_prompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_rejected_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/train/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "bdd2d6b467aaafb5",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

autotrain-data/validation/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7326a56f21da6969d01fb2c9f15286a477dc5f0adee72d9c06dbf87eb0dd87
+size 141512

autotrain-data/validation/dataset_info.json

@@ -0,0 +1,56 @@
+{
+  "citation": "",
+  "description": "",
+  "features": {
+    "Unnamed: 0": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 1": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 2": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 5": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 6": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "Unnamed: 7": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 8": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 9": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "Unnamed: 10": {
+      "dtype": "float64",
+      "_type": "Value"
+    },
+    "autotrain_text": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_prompt": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "autotrain_rejected_text": {
+      "dtype": "string",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": ""
+}

autotrain-data/validation/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "bdd2d6b467aaafb5",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

runs/Jun11_05-20-52_DESKTOP-5GSHRJ7/events.out.tfevents.1718054457.DESKTOP-5GSHRJ7.5384.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67f0cae570cd800e55e38c7c5c9091b538c2c0282653f9710cd4078fef19f2a8
-size 5263
+oid sha256:446d38faa6f62da6ac7d5a868126bbc68b9a6c2416739ff572d4048f2d1a6476
+size 8315

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "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 %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BioGptTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441189a406de460b4a47c4e9d293f7a3d857d4765ff2424e7926e9010c4ca0a0
+size 5112

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "microsoft/biogpt",
+    "project_name": "TEST20",
+    "data_path": "TEST20/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "dpo",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 128,
+    "max_completion_length": null,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "username": "James520"
+}