iyashnayi/SocioLens-llama-3.2-3B
Browse files- README.md +1 -1
- adapter_config.json +20 -7
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yashnayi00-university-of-new-haven/huggingface/runs/
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yashnayi00-university-of-new-haven/huggingface/runs/2qg27orl)
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
@@ -1,23 +1,36 @@
|
|
1 |
{
|
|
|
2 |
"auto_mapping": null,
|
3 |
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
4 |
"bias": "none",
|
|
|
|
|
|
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
7 |
"init_lora_weights": true,
|
|
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
10 |
-
"
|
11 |
-
"
|
|
|
|
|
|
|
|
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
-
"r":
|
|
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
-
"q_proj",
|
18 |
"k_proj",
|
19 |
-
"
|
20 |
-
"
|
|
|
21 |
],
|
22 |
-
"task_type": "CAUSAL_LM"
|
|
|
|
|
|
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "meta-llama/Llama-3.2-3B",
|
5 |
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
11 |
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
"layers_pattern": null,
|
14 |
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.15,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
"modules_to_save": null,
|
22 |
"peft_type": "LORA",
|
23 |
+
"r": 8,
|
24 |
+
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
|
|
27 |
"k_proj",
|
28 |
+
"o_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj"
|
31 |
],
|
32 |
+
"task_type": "CAUSAL_LM",
|
33 |
+
"trainable_token_indices": null,
|
34 |
+
"use_dora": false,
|
35 |
+
"use_rslora": false
|
36 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c3be50ee8fbeaeb3e67984c730e276a795074a7c46176ffa70c37f34e226b8d
|
3 |
+
size 18379784
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dd2014c21bd34ab1494eee9ca8bccc38c94b5a65cb51c6169b0081d798ff27f
|
3 |
size 5624
|