se1250 commited on
Commit
9aae0bb
1 Parent(s): c9bf26b

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation-inference
5
+ - text-generation
6
+ - peft
7
+ library_name: transformers
8
+ base_model: microsoft/DialoGPT-medium
9
+ widget:
10
+ - messages:
11
+ - role: user
12
+ content: What is your favorite condiment?
13
+ license: other
14
+ ---
15
+
16
+ # Model Trained Using AutoTrain
17
+
18
+ This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
19
+
20
+ # Usage
21
+
22
+ ```python
23
+
24
+ from transformers import AutoModelForCausalLM, AutoTokenizer
25
+
26
+ model_path = "PATH_TO_THIS_REPO"
27
+
28
+ tokenizer = AutoTokenizer.from_pretrained(model_path)
29
+ model = AutoModelForCausalLM.from_pretrained(
30
+ model_path,
31
+ device_map="auto",
32
+ torch_dtype='auto'
33
+ ).eval()
34
+
35
+ # Prompt content: "hi"
36
+ messages = [
37
+ {"role": "user", "content": "hi"}
38
+ ]
39
+
40
+ input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
41
+ output_ids = model.generate(input_ids.to('cuda'))
42
+ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
43
+
44
+ # Model response: "Hello! How can I assist you today?"
45
+ print(response)
46
+ ```
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "microsoft/DialoGPT-medium",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "c_attn",
24
+ "c_proj",
25
+ "c_fc"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_dora": false,
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dfb84e2d8cdd17b46cca3a6328469233852a56f2bb0bc319ac43b9ddcab0969
3
+ size 25190568
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Oct17_13-41-51_DESKTOP-4C2BA5E/events.out.tfevents.1729165314.DESKTOP-4C2BA5E.4375.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb4ebc3046ecdbcaacefa1bc7f02aef12ea9a7012394cd2952ee49dbc86a01f
3
+ size 6343
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
16
+ "clean_up_tokenization_spaces": true,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004c034e338da8dab7520c2eb0b87e27ba7065dda0c7840b43c8f7e8f79702cc
3
+ size 5496
training_params.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "microsoft/DialoGPT-medium",
3
+ "project_name": "autotrain-1jpos-1vzp2",
4
+ "data_path": "autotrain-1jpos-1vzp2/autotrain-data",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": true,
8
+ "block_size": 1024,
9
+ "model_max_length": 2048,
10
+ "padding": "right",
11
+ "trainer": "sft",
12
+ "use_flash_attention_2": false,
13
+ "log": "tensorboard",
14
+ "disable_gradient_checkpointing": false,
15
+ "logging_steps": -1,
16
+ "eval_strategy": "epoch",
17
+ "save_total_limit": 1,
18
+ "auto_find_batch_size": false,
19
+ "mixed_precision": "fp16",
20
+ "lr": 3e-05,
21
+ "epochs": 3,
22
+ "batch_size": 2,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 4,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": "none",
31
+ "quantization": "int4",
32
+ "target_modules": "all-linear",
33
+ "merge_adapter": false,
34
+ "peft": true,
35
+ "lora_r": 16,
36
+ "lora_alpha": 32,
37
+ "lora_dropout": 0.05,
38
+ "model_ref": null,
39
+ "dpo_beta": 0.1,
40
+ "max_prompt_length": 128,
41
+ "max_completion_length": null,
42
+ "prompt_text_column": "autotrain_prompt",
43
+ "text_column": "autotrain_text",
44
+ "rejected_text_column": "autotrain_rejected_text",
45
+ "push_to_hub": true,
46
+ "username": "se1250",
47
+ "unsloth": false,
48
+ "distributed_backend": "ddp"
49
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff