Instructions to use TuringGame/Llama-3.2-1B-Instruct-tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use TuringGame/Llama-3.2-1B-Instruct-tuned with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct") model = PeftModel.from_pretrained(base_model, "TuringGame/Llama-3.2-1B-Instruct-tuned") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
|
| 4 |
+
"encoder_dropout": 0.0,
|
| 5 |
+
"encoder_hidden_size": 128,
|
| 6 |
+
"encoder_num_layers": 2,
|
| 7 |
+
"encoder_reparameterization_type": "MLP",
|
| 8 |
+
"inference_mode": true,
|
| 9 |
+
"num_attention_heads": 32,
|
| 10 |
+
"num_layers": 16,
|
| 11 |
+
"num_transformer_submodules": 1,
|
| 12 |
+
"num_virtual_tokens": 20,
|
| 13 |
+
"peft_type": "P_TUNING",
|
| 14 |
+
"revision": null,
|
| 15 |
+
"task_type": "CAUSAL_LM",
|
| 16 |
+
"token_dim": 2048
|
| 17 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6bda0ebefe2bd87aa1d9b74a81702491179b6f6a6b87faf04087fb7e8ca6160
|
| 3 |
+
size 163960
|
runs/May09_10-05-04_42daf13323c9/events.out.tfevents.1746785106.42daf13323c9.1879.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7896e9f817a401d8925d1a1058bc1c00567e73d81fdcf8cddade5897744664b
|
| 3 |
+
size 7321
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:775810950dd573d458c8c26263da5b36fce33394117ce437ecac0a4168a60093
|
| 3 |
+
size 5368
|