hamedrahimi commited on
Commit
94d02cc
·
verified ·
1 Parent(s): 74f62c9

Upload 8 files

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- library_name: transformers
3
- tags: []
4
  ---
5
 
6
  # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
1
  ---
2
+ base_model: google/paligemma2-3b-mix-224
3
+ library_name: peft
4
  ---
5
 
6
  # Model Card for Model ID
 
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
+
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
 
196
 
197
  ## Model Card Contact
198
 
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.13.2
adapter_config.json CHANGED
@@ -3,9 +3,6 @@
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "google/paligemma2-3b-mix-224",
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,
@@ -14,7 +11,6 @@
14
  "layers_to_transform": null,
15
  "loftq_config": {},
16
  "lora_alpha": 32,
17
- "lora_bias": false,
18
  "lora_dropout": 0.05,
19
  "megatron_config": null,
20
  "megatron_core": "megatron.core",
@@ -24,16 +20,15 @@
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "o_proj",
28
- "v_proj",
29
  "k_proj",
30
- "down_proj",
31
  "gate_proj",
 
 
32
  "up_proj",
33
- "q_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
- "trainable_token_indices": null,
37
  "use_dora": false,
38
  "use_rslora": false
39
  }
 
3
  "auto_mapping": null,
4
  "base_model_name_or_path": "google/paligemma2-3b-mix-224",
5
  "bias": "none",
 
 
 
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
8
  "init_lora_weights": true,
 
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
  "lora_alpha": 32,
 
14
  "lora_dropout": 0.05,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "k_proj",
24
+ "v_proj",
25
  "gate_proj",
26
+ "q_proj",
27
+ "down_proj",
28
  "up_proj",
29
+ "o_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
 
32
  "use_dora": false,
33
  "use_rslora": false
34
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b453353fe25701748063ab2f641c70987694041fb8e3aff78a575b1b9813d3
3
- size 47586024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6539b77bc9aed7dc918910c68ed0a077215a3500748175fdf00df1d37c4fbf6
3
+ size 95091968
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882f5995d607120782db6bd18a91b78a85bf2448ac403711dd16a65fa0c003eb
3
+ size 177067885
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12bd36d197fececea5785e1700cff3230099e967e819c33c9687e2d513a0427
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee3f99a053745d2a79ee8e0484c666a074aa17a6222120eda9b13716fb5e96a
3
+ size 1465
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8352e7e8fc5d051fa5fa107f8ef4eccf59cf677bed62f059335768858d425e0b
3
+ size 5713