Add files using upload-large-folder tool
Browse files- config.json +10 -5
- generation_config.json +1 -1
- model.safetensors +2 -2
- preprocessor_config.json +2 -2
- tokenizer_config.json +1 -0
config.json
CHANGED
@@ -1,10 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"Qwen2VLForConditionalGeneration"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id": 151643,
|
8 |
"eos_token_id": 151645,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 1536,
|
@@ -27,7 +26,12 @@
|
|
27 |
"bnb_4bit_use_double_quant": true,
|
28 |
"llm_int8_enable_fp32_cpu_offload": false,
|
29 |
"llm_int8_has_fp16_weight": false,
|
30 |
-
"llm_int8_skip_modules":
|
|
|
|
|
|
|
|
|
|
|
31 |
"llm_int8_threshold": 6.0,
|
32 |
"load_in_4bit": true,
|
33 |
"load_in_8bit": false,
|
@@ -47,7 +51,7 @@
|
|
47 |
"sliding_window": 32768,
|
48 |
"tie_word_embeddings": true,
|
49 |
"torch_dtype": "bfloat16",
|
50 |
-
"transformers_version": "4.
|
51 |
"unsloth_fixed": true,
|
52 |
"use_cache": true,
|
53 |
"use_sliding_window": false,
|
@@ -56,7 +60,8 @@
|
|
56 |
"hidden_size": 1536,
|
57 |
"in_chans": 3,
|
58 |
"model_type": "qwen2_vl",
|
59 |
-
"spatial_patch_size": 14
|
|
|
60 |
},
|
61 |
"vision_end_token_id": 151653,
|
62 |
"vision_start_token_id": 151652,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/Qwen2-VL-2B-Instruct",
|
3 |
"architectures": [
|
4 |
"Qwen2VLForConditionalGeneration"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
|
|
7 |
"eos_token_id": 151645,
|
8 |
"hidden_act": "silu",
|
9 |
"hidden_size": 1536,
|
|
|
26 |
"bnb_4bit_use_double_quant": true,
|
27 |
"llm_int8_enable_fp32_cpu_offload": false,
|
28 |
"llm_int8_has_fp16_weight": false,
|
29 |
+
"llm_int8_skip_modules": [
|
30 |
+
"lm_head",
|
31 |
+
"multi_modal_projector",
|
32 |
+
"merger",
|
33 |
+
"modality_projection"
|
34 |
+
],
|
35 |
"llm_int8_threshold": 6.0,
|
36 |
"load_in_4bit": true,
|
37 |
"load_in_8bit": false,
|
|
|
51 |
"sliding_window": 32768,
|
52 |
"tie_word_embeddings": true,
|
53 |
"torch_dtype": "bfloat16",
|
54 |
+
"transformers_version": "4.49.0",
|
55 |
"unsloth_fixed": true,
|
56 |
"use_cache": true,
|
57 |
"use_sliding_window": false,
|
|
|
60 |
"hidden_size": 1536,
|
61 |
"in_chans": 3,
|
62 |
"model_type": "qwen2_vl",
|
63 |
+
"spatial_patch_size": 14,
|
64 |
+
"torch_dtype": "bfloat16"
|
65 |
},
|
66 |
"vision_end_token_id": 151653,
|
67 |
"vision_start_token_id": 151652,
|
generation_config.json
CHANGED
@@ -10,5 +10,5 @@
|
|
10 |
"temperature": 0.01,
|
11 |
"top_k": 1,
|
12 |
"top_p": 0.001,
|
13 |
-
"transformers_version": "4.
|
14 |
}
|
|
|
10 |
"temperature": 0.01,
|
11 |
"top_k": 1,
|
12 |
"top_p": 0.001,
|
13 |
+
"transformers_version": "4.49.0"
|
14 |
}
|
model.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 sha256:98fea3f60276743a2d1d77787c572e43b5e42df35c166595300d4c38c05a2339
|
3 |
+
size 1540410673
|
preprocessor_config.json
CHANGED
@@ -22,8 +22,8 @@
|
|
22 |
"resample": 3,
|
23 |
"rescale_factor": 0.00392156862745098,
|
24 |
"size": {
|
25 |
-
"
|
26 |
-
"
|
27 |
},
|
28 |
"temporal_patch_size": 2
|
29 |
}
|
|
|
22 |
"resample": 3,
|
23 |
"rescale_factor": 0.00392156862745098,
|
24 |
"size": {
|
25 |
+
"longest_edge": 12845056,
|
26 |
+
"shortest_edge": 3136
|
27 |
},
|
28 |
"temporal_patch_size": 2
|
29 |
}
|
tokenizer_config.json
CHANGED
@@ -134,6 +134,7 @@
|
|
134 |
"clean_up_tokenization_spaces": false,
|
135 |
"eos_token": "<|im_end|>",
|
136 |
"errors": "replace",
|
|
|
137 |
"model_max_length": 32768,
|
138 |
"pad_token": "<|vision_pad|>",
|
139 |
"padding_side": "left",
|
|
|
134 |
"clean_up_tokenization_spaces": false,
|
135 |
"eos_token": "<|im_end|>",
|
136 |
"errors": "replace",
|
137 |
+
"extra_special_tokens": {},
|
138 |
"model_max_length": 32768,
|
139 |
"pad_token": "<|vision_pad|>",
|
140 |
"padding_side": "left",
|