Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +20 -19
- adapter_config.json +37 -0
- adapter_model.safetensors +3 -0
README.md
CHANGED
@@ -1,27 +1,28 @@
|
|
1 |
---
|
2 |
language:
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
thumbnail:
|
12 |
tags:
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
|
|
19 |
datasets:
|
20 |
-
|
21 |
metrics:
|
22 |
-
|
23 |
-
|
24 |
-
base_model:
|
25 |
---
|
26 |
|
27 |
# Marites AI 🗣️🔥
|
|
|
1 |
---
|
2 |
language:
|
3 |
+
- en
|
4 |
+
- tl
|
5 |
+
- ceb
|
6 |
+
- war
|
7 |
+
- hil
|
8 |
+
- pam
|
9 |
+
- bcl
|
10 |
+
- ilo
|
11 |
+
thumbnail: https://res.cloudinary.com/digpzthsf/image/upload/v1738737064/grdtuk20lbskymaenvvt.jpg
|
12 |
tags:
|
13 |
+
- deepseek
|
14 |
+
- distill
|
15 |
+
- gossip
|
16 |
+
- philippines
|
17 |
+
- multi-language
|
18 |
+
- unsloth
|
19 |
+
license: mit
|
20 |
datasets:
|
21 |
+
- filipino-gossip-dataset
|
22 |
metrics:
|
23 |
+
- accuracy
|
24 |
+
- perplexity
|
25 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
26 |
---
|
27 |
|
28 |
# Marites AI 🗣️🔥
|
adapter_config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
|
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,
|
11 |
+
"layer_replication": null,
|
12 |
+
"layers_pattern": null,
|
13 |
+
"layers_to_transform": null,
|
14 |
+
"loftq_config": {},
|
15 |
+
"lora_alpha": 16,
|
16 |
+
"lora_bias": false,
|
17 |
+
"lora_dropout": 0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"gate_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"q_proj",
|
30 |
+
"o_proj",
|
31 |
+
"up_proj",
|
32 |
+
"v_proj"
|
33 |
+
],
|
34 |
+
"task_type": "CAUSAL_LM",
|
35 |
+
"use_dora": false,
|
36 |
+
"use_rslora": false
|
37 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5998b730ca28b561ea2be0953aaa0acf1c71430330afaff20e29b76e590f1b7
|
3 |
+
size 167832240
|