OumaymaeELBIACH/Llama-3.2-1B
Browse files- README.md +5 -4
- adapter_config.json +11 -3
- adapter_model.safetensors +2 -2
- runs/Dec28_11-57-34_98a9f987451e/events.out.tfevents.1735387732.98a9f987451e.2637.0 +3 -0
- runs/Dec28_12-28-31_98a9f987451e/events.out.tfevents.1735388922.98a9f987451e.2637.1 +3 -0
- runs/Dec28_12-29-45_98a9f987451e/events.out.tfevents.1735388992.98a9f987451e.2637.2 +3 -0
- runs/Dec28_12-29-45_98a9f987451e/events.out.tfevents.1735389115.98a9f987451e.2637.3 +3 -0
- runs/Dec28_12-32-30_98a9f987451e/events.out.tfevents.1735389169.98a9f987451e.2637.4 +3 -0
- runs/Dec28_12-39-31_98a9f987451e/events.out.tfevents.1735389580.98a9f987451e.2637.5 +3 -0
- runs/Dec28_12-41-49_98a9f987451e/events.out.tfevents.1735389720.98a9f987451e.2637.6 +3 -0
- runs/Dec28_12-41-49_98a9f987451e/events.out.tfevents.1735389915.98a9f987451e.2637.7 +3 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -27,17 +27,18 @@ print(output["generated_text"])
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
|
|
30 |
|
31 |
|
32 |
This model was trained with SFT.
|
33 |
|
34 |
### Framework versions
|
35 |
|
36 |
-
- TRL: 0.
|
37 |
-
- Transformers: 4.
|
38 |
- Pytorch: 2.5.1+cu121
|
39 |
-
- Datasets: 3.
|
40 |
-
- Tokenizers: 0.
|
41 |
|
42 |
## Citations
|
43 |
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
34 |
|
35 |
### Framework versions
|
36 |
|
37 |
+
- TRL: 0.13.0
|
38 |
+
- Transformers: 4.48.0.dev0
|
39 |
- Pytorch: 2.5.1+cu121
|
40 |
+
- Datasets: 3.2.0
|
41 |
+
- Tokenizers: 0.21.0
|
42 |
|
43 |
## Citations
|
44 |
|
adapter_config.json
CHANGED
@@ -1,8 +1,10 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
|
|
|
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
@@ -11,16 +13,22 @@
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 16,
|
14 |
-
"
|
|
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"v_proj",
|
|
|
|
|
|
|
24 |
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
"bias": "none",
|
6 |
+
"eva_config": null,
|
7 |
+
"exclude_modules": null,
|
8 |
"fan_in_fan_out": false,
|
9 |
"inference_mode": true,
|
10 |
"init_lora_weights": true,
|
|
|
13 |
"layers_to_transform": null,
|
14 |
"loftq_config": {},
|
15 |
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0.05,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": null,
|
21 |
"peft_type": "LORA",
|
22 |
+
"r": 32,
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"k_proj",
|
27 |
+
"down_proj",
|
28 |
"v_proj",
|
29 |
+
"gate_proj",
|
30 |
+
"o_proj",
|
31 |
+
"up_proj",
|
32 |
"q_proj"
|
33 |
],
|
34 |
"task_type": "CAUSAL_LM",
|
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 sha256:2f1899b3a34b3ffdf37183d38ab11eeefc73aa1f2ae8d73109040919444d8822
|
3 |
+
size 90211056
|
runs/Dec28_11-57-34_98a9f987451e/events.out.tfevents.1735387732.98a9f987451e.2637.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e466a087bffc2ad40dc4fd84cb55a32bc001d9cc164a01db4d9b91fee4cd72e
|
3 |
+
size 12293
|
runs/Dec28_12-28-31_98a9f987451e/events.out.tfevents.1735388922.98a9f987451e.2637.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b83c2ce77315e2d776e16dbe8f7f32fcc83aeacb18f2a203324763f0dc7e13d8
|
3 |
+
size 7150
|
runs/Dec28_12-29-45_98a9f987451e/events.out.tfevents.1735388992.98a9f987451e.2637.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17252feaf7c9b17abab8422f2c5eeb676a4acae7c766f3228799c53a6fcdb390
|
3 |
+
size 8612
|
runs/Dec28_12-29-45_98a9f987451e/events.out.tfevents.1735389115.98a9f987451e.2637.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbde96b7e45728f75cab444baf508a45a70924565b5e3ef42f6a12f917c0b23
|
3 |
+
size 359
|
runs/Dec28_12-32-30_98a9f987451e/events.out.tfevents.1735389169.98a9f987451e.2637.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a73a075a3e5678126ba5bf5e26e3bfffe05470451b8038a63c4e4c4c5c83a579
|
3 |
+
size 8065
|
runs/Dec28_12-39-31_98a9f987451e/events.out.tfevents.1735389580.98a9f987451e.2637.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:559d9230cfeae739d7a86a67544741c27ad795cba81c41205fed7c4c78570be7
|
3 |
+
size 9338
|
runs/Dec28_12-41-49_98a9f987451e/events.out.tfevents.1735389720.98a9f987451e.2637.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3758a15f9334ec76ab869a8a181c2aa0fd05e70fb51da3fa61d2edccdb5b977
|
3 |
+
size 12293
|
runs/Dec28_12-41-49_98a9f987451e/events.out.tfevents.1735389915.98a9f987451e.2637.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3875ac9ee87bd9d91c53556ec4098e52289b70f604048e781a0874507272e11f
|
3 |
+
size 359
|
tokenizer_config.json
CHANGED
@@ -2057,7 +2057,7 @@
|
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
-
"model_max_length":
|
2061 |
"pad_token": "<|end_of_text|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
|
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
+
"model_max_length": 512,
|
2061 |
"pad_token": "<|end_of_text|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e25a9f108a56883d0624e13cab53d79daed3fb00f5e4e0d0bc3415a753fa4ac0
|
3 |
size 5560
|