devichand commited on
Commit
3718505
·
verified ·
1 Parent(s): 3e97c43

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - devichand/gemma-3-1b-dare-peft-codealpaca
4
+ - devichand/gemma-3-1b-peft-safe
5
+ - google/gemma-3-1b-pt
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+
11
+ ---
12
+ # merge
13
+
14
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
15
+
16
+ ## Merge Details
17
+ ### Merge Method
18
+
19
+ This model was merged using the [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [google/gemma-3-1b-pt](https://huggingface.co/google/gemma-3-1b-pt) as a base.
20
+
21
+ ### Models Merged
22
+
23
+ The following models were included in the merge:
24
+ * [devichand/gemma-3-1b-dare-peft-codealpaca](https://huggingface.co/devichand/gemma-3-1b-dare-peft-codealpaca)
25
+ * [devichand/gemma-3-1b-peft-safe](https://huggingface.co/devichand/gemma-3-1b-peft-safe)
26
+
27
+ ### Configuration
28
+
29
+ The following YAML configuration was used to produce this model:
30
+
31
+ ```yaml
32
+
33
+ models:
34
+ - model: devichand/gemma-3-1b-dare-peft-codealpaca
35
+ parameters:
36
+ weight: 1.0
37
+
38
+ - model: devichand/gemma-3-1b-peft-safe
39
+ parameters:
40
+ weight: 1.0
41
+ lambda: 0.5
42
+
43
+ merge_method: task_arithmetic
44
+ base_model: google/gemma-3-1b-pt
45
+ parameters:
46
+ int8_mask: true
47
+ dtype: bfloat16
48
+
49
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": null,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "eos_token_id": 1,
11
+ "final_logit_softcapping": null,
12
+ "head_dim": 256,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 1152,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 6912,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "gemma3_text",
19
+ "num_attention_heads": 4,
20
+ "num_hidden_layers": 26,
21
+ "num_key_value_heads": 1,
22
+ "pad_token_id": 0,
23
+ "query_pre_attn_scalar": 256,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_local_base_freq": 10000,
26
+ "rope_scaling": null,
27
+ "rope_theta": 1000000,
28
+ "sliding_window": 512,
29
+ "sliding_window_pattern": 6,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.50.3",
32
+ "use_cache": true,
33
+ "vocab_size": 262144
34
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ models:
3
+ - model: devichand/gemma-3-1b-dare-peft-codealpaca
4
+ parameters:
5
+ weight: 1.0
6
+
7
+ - model: devichand/gemma-3-1b-peft-safe
8
+ parameters:
9
+ weight: 1.0
10
+ lambda: 0.5
11
+
12
+ merge_method: task_arithmetic
13
+ base_model: google/gemma-3-1b-pt
14
+ parameters:
15
+ int8_mask: true
16
+ dtype: bfloat16
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fcd64299e97dea996d5d0fe80769f048d18caf59228040b50c505e76f6df51
3
+ size 1999811208
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
3
+ size 33384570
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff