Upload LlavaForConditionalGeneration
Browse files- README.md +2 -2
- config.json +7 -9
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
|
|
|
|
2 |
datasets:
|
3 |
- Lin-Chen/ShareGPT4V
|
4 |
pipeline_tag: image-text-to-text
|
5 |
-
library_name: xtuner
|
6 |
-
license: llama3
|
7 |
---
|
8 |
|
9 |
---
|
|
|
1 |
---
|
2 |
+
license: llama3
|
3 |
+
library_name: xtuner
|
4 |
datasets:
|
5 |
- Lin-Chen/ShareGPT4V
|
6 |
pipeline_tag: image-text-to-text
|
|
|
|
|
7 |
---
|
8 |
|
9 |
---
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"LlavaForConditionalGeneration"
|
4 |
],
|
@@ -12,19 +13,17 @@
|
|
12 |
"architectures": [
|
13 |
"LlamaForCausalLM"
|
14 |
],
|
|
|
15 |
"max_position_embeddings": 8192,
|
16 |
"model_type": "llama",
|
|
|
17 |
"rms_norm_eps": 1e-05,
|
18 |
"torch_dtype": "float16",
|
19 |
-
"vocab_size": 128256
|
20 |
-
"num_attention_heads": 32,
|
21 |
-
"num_hidden_layers": 32,
|
22 |
-
"num_key_value_heads": 8,
|
23 |
-
"intermediate_size": 14336
|
24 |
},
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "float16",
|
27 |
-
"transformers_version": "4.
|
28 |
"vision_config": {
|
29 |
"hidden_size": 1024,
|
30 |
"image_size": 336,
|
@@ -37,6 +36,5 @@
|
|
37 |
"vocab_size": 32000
|
38 |
},
|
39 |
"vision_feature_layer": -2,
|
40 |
-
"vision_feature_select_strategy": "default"
|
41 |
-
|
42 |
-
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "xtuner/llava-llama-3-8b-v1_1-hf",
|
3 |
"architectures": [
|
4 |
"LlavaForConditionalGeneration"
|
5 |
],
|
|
|
13 |
"architectures": [
|
14 |
"LlamaForCausalLM"
|
15 |
],
|
16 |
+
"intermediate_size": 14336,
|
17 |
"max_position_embeddings": 8192,
|
18 |
"model_type": "llama",
|
19 |
+
"num_key_value_heads": 8,
|
20 |
"rms_norm_eps": 1e-05,
|
21 |
"torch_dtype": "float16",
|
22 |
+
"vocab_size": 128256
|
|
|
|
|
|
|
|
|
23 |
},
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.40.0",
|
27 |
"vision_config": {
|
28 |
"hidden_size": 1024,
|
29 |
"image_size": 336,
|
|
|
36 |
"vocab_size": 32000
|
37 |
},
|
38 |
"vision_feature_layer": -2,
|
39 |
+
"vision_feature_select_strategy": "default"
|
40 |
+
}
|
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
"eos_token_id": 128001,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 128000,
|
4 |
"eos_token_id": 128001,
|
5 |
+
"transformers_version": "4.40.0"
|
6 |
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779b08a5e49134a8794c97b0010859aa757281089b2293b17a7f175798427e69
|
3 |
+
size 4954605072
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268d2a5b0427bf992dd67e79fd1db200b6f95be61867bfe9345d370be2e6c68a
|
3 |
+
size 4915917552
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8e9275cbb4ffa5607ce95502532aae71377284b251efe4c71f76883318f9ba
|
3 |
+
size 4999820824
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e0a846205f02e2fe463cad9c6a7f9785292444ca266b8baa786a71127db32b
|
3 |
+
size 1839245336
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|