Gaoussin commited on
Commit
bb97072
·
verified ·
1 Parent(s): ba9a01e

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: cc-by-nc-sa-4.0
4
+ base_model: unsloth/llama-outetts-1.0-1b
5
+ tags:
6
+ - base_model:adapter:unsloth/llama-outetts-1.0-1b
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ - unsloth
12
+ pipeline_tag: text-generation
13
+ model-index:
14
+ - name: outetts-v3
15
+ results: []
16
+ ---
17
+
18
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
19
+ should probably proofread and complete it, then remove this comment. -->
20
+
21
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/bamalingua-bamalingua/Bamalingua-speech-oute-3/runs/fcfgmaje)
22
+ # outetts-v3
23
+
24
+ This model is a fine-tuned version of [unsloth/llama-outetts-1.0-1b](https://huggingface.co/unsloth/llama-outetts-1.0-1b) on an unknown dataset.
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 0.0002
44
+ - train_batch_size: 1
45
+ - eval_batch_size: 4
46
+ - seed: 3407
47
+ - gradient_accumulation_steps: 8
48
+ - total_train_batch_size: 8
49
+ - optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - lr_scheduler_warmup_steps: 5
53
+ - num_epochs: 1
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Framework versions
57
+
58
+ - PEFT 0.18.1
59
+ - Transformers 4.56.2
60
+ - Pytorch 2.8.0+cu126
61
+ - Datasets 3.6.0
62
+ - Tokenizers 0.22.1
adapter_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": {
6
+ "base_model_class": "LlamaForCausalLM",
7
+ "parent_library": "transformers.models.llama.modeling_llama",
8
+ "unsloth_fixed": true
9
+ },
10
+ "base_model_name_or_path": "unsloth/llama-outetts-1.0-1b",
11
+ "bias": "none",
12
+ "corda_config": null,
13
+ "ensure_weight_tying": false,
14
+ "eva_config": null,
15
+ "exclude_modules": null,
16
+ "fan_in_fan_out": false,
17
+ "inference_mode": true,
18
+ "init_lora_weights": true,
19
+ "layer_replication": null,
20
+ "layers_pattern": null,
21
+ "layers_to_transform": null,
22
+ "loftq_config": {},
23
+ "lora_alpha": 64,
24
+ "lora_bias": false,
25
+ "lora_dropout": 0,
26
+ "megatron_config": null,
27
+ "megatron_core": "megatron.core",
28
+ "modules_to_save": null,
29
+ "peft_type": "LORA",
30
+ "peft_version": "0.18.1",
31
+ "qalora_group_size": 16,
32
+ "r": 64,
33
+ "rank_pattern": {},
34
+ "revision": null,
35
+ "target_modules": [
36
+ "up_proj",
37
+ "gate_proj",
38
+ "k_proj",
39
+ "down_proj",
40
+ "o_proj",
41
+ "v_proj",
42
+ "q_proj"
43
+ ],
44
+ "target_parameters": null,
45
+ "task_type": "CAUSAL_LM",
46
+ "trainable_token_indices": null,
47
+ "use_dora": false,
48
+ "use_qalora": false,
49
+ "use_rslora": false
50
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f796cca25045058f7d7e1e5e9029b9dc502c3b7a58e53687fd71895bf041a2f
3
+ size 180385008
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ outetts-1.0
special_tokens_map.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec54a55e3c6fc7318ea02cbd1a6eb1fb180bff1b58acbf068504a25f1b407b7b
3
+ size 18366636
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc1dfb805d395fee6e86d9ea94f04f29e45aa0b4f053cfe6ef5381f7177f504
3
+ size 6289