akshitad commited on
Commit
3f40079
·
verified ·
1 Parent(s): 01fb939

Upload 17 files

Browse files
mixtral-8-7B-v1-finetuned-multilabel/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: mistralai/Mixtral-8x7B-v0.1
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
+ ```
mixtral-8-7B-v1-finetuned-multilabel/adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-v0.1",
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": 0.0,
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
+ "w1",
24
+ "w3",
25
+ "w2",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "o_proj",
30
+ "gate"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
mixtral-8-7B-v1-finetuned-multilabel/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a57046bbf21dfac3f61e68ece4cbb4e097b8cb4c69b5f564e3501df2603884
3
+ size 969174880
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/dataset_dict.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"splits": ["train", "validation"]}
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/train/cache-2df4dbe001e9d2eb.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5eb230731020c2dd8b4e7e9c441bfd0ef0074e1fb63ae380ff8aafd94b13693
3
+ size 9317728
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/train/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8209b5a3e738d1c6d3a78bb10142a07e146e117def7c5a1748dc2d5770c158d
3
+ size 9526056
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/train/dataset_info.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "autotrain_text": {
6
+ "dtype": "string",
7
+ "_type": "Value"
8
+ }
9
+ },
10
+ "homepage": "",
11
+ "license": ""
12
+ }
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/train/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "a10a237b7a90b27d",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/validation/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32351399ac129d9ba687f080992416d8767b7f710dd724ce79fb7c52702ee951
3
+ size 3147168
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/validation/dataset_info.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "citation": "",
3
+ "description": "",
4
+ "features": {
5
+ "autotrain_text": {
6
+ "dtype": "string",
7
+ "_type": "Value"
8
+ }
9
+ },
10
+ "homepage": "",
11
+ "license": ""
12
+ }
mixtral-8-7B-v1-finetuned-multilabel/autotrain-data/validation/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "f111e5ec0c58ce88",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": null
13
+ }
mixtral-8-7B-v1-finetuned-multilabel/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
mixtral-8-7B-v1-finetuned-multilabel/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
mixtral-8-7B-v1-finetuned-multilabel/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
mixtral-8-7B-v1-finetuned-multilabel/tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "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 %}",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": true,
37
+ "model_max_length": 8192,
38
+ "pad_token": "</s>",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false
44
+ }
mixtral-8-7B-v1-finetuned-multilabel/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84520beb00ce663d8f696186ebda684d58aa28b02a3cee91660bc265c0cdbb62
3
+ size 5496
mixtral-8-7B-v1-finetuned-multilabel/training_params.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "mistralai/Mixtral-8x7B-v0.1",
3
+ "project_name": "mixtral-8-7B-v1-finetuned-apsv",
4
+ "data_path": "mixtral-8-7B-v1-finetuned-apsv/autotrain-data",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "add_eos_token": false,
8
+ "block_size": -1,
9
+ "model_max_length": 8192,
10
+ "padding": null,
11
+ "trainer": "sft",
12
+ "use_flash_attention_2": false,
13
+ "log": "none",
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": 0.0003,
21
+ "epochs": 3,
22
+ "batch_size": 12,
23
+ "warmup_ratio": 0.1,
24
+ "gradient_accumulation": 1,
25
+ "optimizer": "adamw_torch",
26
+ "scheduler": "linear",
27
+ "weight_decay": 0.0,
28
+ "max_grad_norm": 1.0,
29
+ "seed": 42,
30
+ "chat_template": "tokenizer",
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": 0.0,
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": false,
46
+ "username": null,
47
+ "token": "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",
48
+ "unsloth": false
49
+ }