Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +2 -0
- config.json +54 -28
- generation_config.json +4 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +2 -2
README.md
CHANGED
@@ -5,6 +5,8 @@ tags:
|
|
5 |
- transformers
|
6 |
- unsloth
|
7 |
- gemma3
|
|
|
|
|
8 |
license: apache-2.0
|
9 |
language:
|
10 |
- en
|
|
|
5 |
- transformers
|
6 |
- unsloth
|
7 |
- gemma3
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
license: apache-2.0
|
11 |
language:
|
12 |
- en
|
config.json
CHANGED
@@ -1,37 +1,63 @@
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
-
"
|
6 |
-
"attention_dropout": 0.0,
|
7 |
-
"attn_logit_softcapping": null,
|
8 |
"bos_token_id": 2,
|
9 |
-
"
|
10 |
-
"eos_token_id":
|
11 |
-
"
|
12 |
-
"head_dim": 256,
|
13 |
-
"hidden_activation": "gelu_pytorch_tanh",
|
14 |
-
"hidden_size": 2560,
|
15 |
"initializer_range": 0.02,
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"model_type": "gemma3_text",
|
19 |
-
"num_attention_heads": 8,
|
20 |
-
"num_hidden_layers": 34,
|
21 |
-
"num_key_value_heads": 4,
|
22 |
"pad_token_id": 0,
|
23 |
-
"
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
},
|
30 |
-
"
|
31 |
-
"sliding_window": 1024,
|
32 |
-
"sliding_window_pattern": 6,
|
33 |
-
"torch_dtype": "float16",
|
34 |
"transformers_version": "4.50.1",
|
35 |
-
"
|
36 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
}
|
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
+
"Gemma3ForConditionalGeneration"
|
4 |
],
|
5 |
+
"boi_token_index": 255999,
|
|
|
|
|
6 |
"bos_token_id": 2,
|
7 |
+
"eoi_token_index": 256000,
|
8 |
+
"eos_token_id": 106,
|
9 |
+
"image_token_index": 262144,
|
|
|
|
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
+
"mm_tokens_per_image": 256,
|
12 |
+
"model_type": "gemma3",
|
|
|
|
|
|
|
|
|
13 |
"pad_token_id": 0,
|
14 |
+
"text_config": {
|
15 |
+
"attention_bias": false,
|
16 |
+
"attention_dropout": 0.0,
|
17 |
+
"attn_logit_softcapping": null,
|
18 |
+
"cache_implementation": "hybrid",
|
19 |
+
"final_logit_softcapping": null,
|
20 |
+
"head_dim": 256,
|
21 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
22 |
+
"hidden_size": 2560,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 10240,
|
25 |
+
"max_position_embeddings": 131072,
|
26 |
+
"model_type": "gemma3_text",
|
27 |
+
"num_attention_heads": 8,
|
28 |
+
"num_hidden_layers": 34,
|
29 |
+
"num_key_value_heads": 4,
|
30 |
+
"query_pre_attn_scalar": 256,
|
31 |
+
"rms_norm_eps": 1e-06,
|
32 |
+
"rope_local_base_freq": 10000.0,
|
33 |
+
"rope_scaling": {
|
34 |
+
"factor": 8.0,
|
35 |
+
"rope_type": "linear"
|
36 |
+
},
|
37 |
+
"rope_theta": 1000000.0,
|
38 |
+
"sliding_window": 1024,
|
39 |
+
"sliding_window_pattern": 6,
|
40 |
+
"torch_dtype": "float16",
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 262208
|
43 |
},
|
44 |
+
"torch_dtype": "bfloat16",
|
|
|
|
|
|
|
45 |
"transformers_version": "4.50.1",
|
46 |
+
"unsloth_fixed": true,
|
47 |
+
"unsloth_version": "2025.3.18",
|
48 |
+
"vision_config": {
|
49 |
+
"attention_dropout": 0.0,
|
50 |
+
"hidden_act": "gelu_pytorch_tanh",
|
51 |
+
"hidden_size": 1152,
|
52 |
+
"image_size": 896,
|
53 |
+
"intermediate_size": 4304,
|
54 |
+
"layer_norm_eps": 1e-06,
|
55 |
+
"model_type": "siglip_vision_model",
|
56 |
+
"num_attention_heads": 16,
|
57 |
+
"num_channels": 3,
|
58 |
+
"num_hidden_layers": 27,
|
59 |
+
"patch_size": 14,
|
60 |
+
"torch_dtype": "float16",
|
61 |
+
"vision_use_head": false
|
62 |
+
}
|
63 |
}
|
generation_config.json
CHANGED
@@ -2,7 +2,10 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 2,
|
4 |
"cache_implementation": "hybrid",
|
5 |
-
"eos_token_id":
|
|
|
|
|
|
|
6 |
"pad_token_id": 0,
|
7 |
"transformers_version": "4.50.1"
|
8 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 2,
|
4 |
"cache_implementation": "hybrid",
|
5 |
+
"eos_token_id": [
|
6 |
+
1,
|
7 |
+
106
|
8 |
+
],
|
9 |
"pad_token_id": 0,
|
10 |
"transformers_version": "4.50.1"
|
11 |
}
|
model-00001-of-00002.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 sha256:0769df1ef8714ebc45242b47b93fd813ded57226edc6312f7435003973df4019
|
3 |
+
size 4961807176
|
model-00002-of-00002.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:f5010993723e5046c6373330e9c71b754534e0db25999c6ad4ff38fb05f705cc
|
3 |
+
size 3639459168
|
model.safetensors.index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
-
"total_size":
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
@@ -887,4 +887,4 @@
|
|
887 |
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
888 |
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
889 |
}
|
890 |
-
}
|
|
|
1 |
{
|
2 |
"metadata": {
|
3 |
+
"total_size": 8601150944
|
4 |
},
|
5 |
"weight_map": {
|
6 |
"language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
|
|
887 |
"vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
|
888 |
"vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
|
889 |
}
|
890 |
+
}
|