nintwentydo commited on
Commit
28ade5b
·
verified ·
1 Parent(s): 05942df

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 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+
8
+ ---
9
+ # pixtral_merge_task_3
10
+
11
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
12
+
13
+ ## Merge Details
14
+ ### Merge Method
15
+
16
+ This model was merged using the [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using /opt/dlami/nvme/models/unsloth_Pixtral-12B-2409 as a base.
17
+
18
+ ### Models Merged
19
+
20
+ The following models were included in the merge:
21
+ * /opt/dlami/nvme/models/TheDrummer_Rocinante-12B-v1.1_llava
22
+ * /opt/dlami/nvme/models/TheDrummer_UnslopNemo-12B-v3_llava
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ merge_method: task_arithmetic
30
+ dtype: bfloat16
31
+ base_model: /opt/dlami/nvme/models/unsloth_Pixtral-12B-2409
32
+ models:
33
+ - model: /opt/dlami/nvme/models/unsloth_Pixtral-12B-2409
34
+ parameters:
35
+ weight: 1.0
36
+ - model: /opt/dlami/nvme/models/TheDrummer_UnslopNemo-12B-v3_llava
37
+ parameters:
38
+ weight: 0.3
39
+ - model: /opt/dlami/nvme/models/TheDrummer_Rocinante-12B-v1.1_llava
40
+ parameters:
41
+ weight: 0.2
42
+ tokenizer:
43
+ source: base
44
+ chat_template: "pixtral12b"
45
+
46
+ ```
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/opt/dlami/nvme/models/unsloth_Pixtral-12B-2409",
3
+ "architectures": [
4
+ "LlavaForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_seq_length": 1,
8
+ "image_token_index": 10,
9
+ "model_type": "llava",
10
+ "num_hidden_layers": 40,
11
+ "projector_hidden_act": "gelu",
12
+ "initializer_range": 0.02,
13
+ "text_config": {
14
+ "hidden_size": 5120,
15
+ "head_dim": 128,
16
+ "intermediate_size": 14336,
17
+ "is_composition": true,
18
+ "max_position_embeddings": 1024000,
19
+ "model_type": "mistral",
20
+ "num_hidden_layers": 40,
21
+ "num_attention_heads": 32,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 1000000000.0,
25
+ "sliding_window": null,
26
+ "vocab_size": 131072
27
+ },
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.47.1",
30
+ "vision_config": {
31
+ "head_dim": 64,
32
+ "num_attention_heads": 16,
33
+ "hidden_act": "silu",
34
+ "image_size": 1024,
35
+ "is_composition": true,
36
+ "model_type": "pixtral",
37
+ "patch_size": 16,
38
+ "rope_theta": 10000.0,
39
+ "tie_word_embeddings": false
40
+ },
41
+ "vision_feature_layer": -1,
42
+ "vision_feature_select_strategy": "full"
43
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: task_arithmetic
2
+ dtype: bfloat16
3
+ base_model: /opt/dlami/nvme/models/unsloth_Pixtral-12B-2409
4
+ models:
5
+ - model: /opt/dlami/nvme/models/unsloth_Pixtral-12B-2409
6
+ parameters:
7
+ weight: 1.0
8
+ - model: /opt/dlami/nvme/models/TheDrummer_UnslopNemo-12B-v3_llava
9
+ parameters:
10
+ weight: 0.3
11
+ - model: /opt/dlami/nvme/models/TheDrummer_Rocinante-12B-v1.1_llava
12
+ parameters:
13
+ weight: 0.2
14
+ tokenizer:
15
+ source: base
16
+ chat_template: "pixtral12b"
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d88ce1ad546d6afaa00ae738c5614e185926a1ac1dd170698ba5d18d56dc8b
3
+ size 25365558112
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "PixtralImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "patch_size": {
18
+ "height": 16,
19
+ "width": 16
20
+ },
21
+ "processor_class": "PixtralProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1024
26
+ }
27
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "[IMG_BREAK]",
3
+ "image_end_token": "[IMG_END]",
4
+ "image_token": "[IMG]",
5
+ "patch_size": 16,
6
+ "processor_class": "PixtralProcessor"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f33e6f52b2833e8cc17229af8eea363f640a898f19a48184a2c7f6f5a88337
3
+ size 17077329
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff