Upload model
Browse files- README.md +1 -52
- adapter_config.json +3 -0
- adapter_model.bin +1 -1
README.md
CHANGED
@@ -1,54 +1,3 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
tags:
|
4 |
-
- generated_from_trainer
|
5 |
-
model-index:
|
6 |
-
- name: empath-llama-7b
|
7 |
-
results: []
|
8 |
---
|
9 |
-
|
10 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
-
should probably proofread and complete it, then remove this comment. -->
|
12 |
-
|
13 |
-
# empath-llama-7b
|
14 |
-
|
15 |
-
This model is a fine-tuned version of [decapoda-research/llama-7b-hf](https://huggingface.co/decapoda-research/llama-7b-hf) on the None dataset.
|
16 |
-
|
17 |
-
## Model description
|
18 |
-
|
19 |
-
More information needed
|
20 |
-
|
21 |
-
## Intended uses & limitations
|
22 |
-
|
23 |
-
More information needed
|
24 |
-
|
25 |
-
## Training and evaluation data
|
26 |
-
|
27 |
-
More information needed
|
28 |
-
|
29 |
-
## Training procedure
|
30 |
-
|
31 |
-
### Training hyperparameters
|
32 |
-
|
33 |
-
The following hyperparameters were used during training:
|
34 |
-
- learning_rate: 0.001
|
35 |
-
- train_batch_size: 4
|
36 |
-
- eval_batch_size: 8
|
37 |
-
- seed: 42
|
38 |
-
- gradient_accumulation_steps: 4
|
39 |
-
- total_train_batch_size: 16
|
40 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
-
- lr_scheduler_type: linear
|
42 |
-
- lr_scheduler_warmup_steps: 100
|
43 |
-
- training_steps: 100
|
44 |
-
|
45 |
-
### Training results
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
### Framework versions
|
50 |
-
|
51 |
-
- Transformers 4.30.0.dev0
|
52 |
-
- Pytorch 2.0.1+cu117
|
53 |
-
- Datasets 2.12.0
|
54 |
-
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
+
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_config.json
CHANGED
@@ -4,11 +4,14 @@
|
|
4 |
"fan_in_fan_out": false,
|
5 |
"inference_mode": true,
|
6 |
"init_lora_weights": true,
|
|
|
|
|
7 |
"lora_alpha": 16,
|
8 |
"lora_dropout": 0.05,
|
9 |
"modules_to_save": null,
|
10 |
"peft_type": "LORA",
|
11 |
"r": 8,
|
|
|
12 |
"target_modules": [
|
13 |
"q_proj",
|
14 |
"k_proj",
|
|
|
4 |
"fan_in_fan_out": false,
|
5 |
"inference_mode": true,
|
6 |
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
"lora_alpha": 16,
|
10 |
"lora_dropout": 0.05,
|
11 |
"modules_to_save": null,
|
12 |
"peft_type": "LORA",
|
13 |
"r": 8,
|
14 |
+
"revision": null,
|
15 |
"target_modules": [
|
16 |
"q_proj",
|
17 |
"k_proj",
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33646413
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e80b1f6067d268ff2976a40443d9086c6f3566150c30f785418ac4424da0765a
|
3 |
size 33646413
|