Pushing loaded in 4bit to hub
Browse files- config.json +70 -0
- generation_config.json +6 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openbmb/MiniCPM-V-2_6",
|
3 |
+
"architectures": [
|
4 |
+
"MiniCPMV"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "openbmb/MiniCPM-V-2_6--configuration_minicpm.MiniCPMVConfig",
|
9 |
+
"AutoModel": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV",
|
10 |
+
"AutoModelForCausalLM": "openbmb/MiniCPM-V-2_6--modeling_minicpmv.MiniCPMV"
|
11 |
+
},
|
12 |
+
"batch_vision_input": true,
|
13 |
+
"bos_token_id": 151643,
|
14 |
+
"drop_vision_last_layer": false,
|
15 |
+
"eos_token_id": 151645,
|
16 |
+
"hidden_act": "silu",
|
17 |
+
"hidden_size": 3584,
|
18 |
+
"image_size": 448,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 18944,
|
21 |
+
"max_position_embeddings": 32768,
|
22 |
+
"max_window_layers": 28,
|
23 |
+
"model_type": "minicpmv",
|
24 |
+
"num_attention_heads": 28,
|
25 |
+
"num_hidden_layers": 28,
|
26 |
+
"num_key_value_heads": 4,
|
27 |
+
"patch_size": 14,
|
28 |
+
"quantization_config": {
|
29 |
+
"_load_in_4bit": true,
|
30 |
+
"_load_in_8bit": false,
|
31 |
+
"bnb_4bit_compute_dtype": "float32",
|
32 |
+
"bnb_4bit_quant_storage": "uint8",
|
33 |
+
"bnb_4bit_quant_type": "fp4",
|
34 |
+
"bnb_4bit_use_double_quant": false,
|
35 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
36 |
+
"llm_int8_has_fp16_weight": false,
|
37 |
+
"llm_int8_skip_modules": null,
|
38 |
+
"llm_int8_threshold": 6.0,
|
39 |
+
"load_in_4bit": true,
|
40 |
+
"load_in_8bit": false,
|
41 |
+
"quant_method": "bitsandbytes"
|
42 |
+
},
|
43 |
+
"query_num": 64,
|
44 |
+
"rms_norm_eps": 1e-06,
|
45 |
+
"rope_theta": 1000000.0,
|
46 |
+
"slice_config": {
|
47 |
+
"max_slice_nums": 9,
|
48 |
+
"model_type": "minicpmv"
|
49 |
+
},
|
50 |
+
"slice_mode": true,
|
51 |
+
"sliding_window": 131072,
|
52 |
+
"tie_word_embeddings": false,
|
53 |
+
"torch_dtype": "float16",
|
54 |
+
"transformers_version": "4.42.4",
|
55 |
+
"use_cache": true,
|
56 |
+
"use_image_id": true,
|
57 |
+
"use_sliding_window": false,
|
58 |
+
"version": 2.6,
|
59 |
+
"vision_batch_size": 16,
|
60 |
+
"vision_config": {
|
61 |
+
"hidden_size": 1152,
|
62 |
+
"image_size": 980,
|
63 |
+
"intermediate_size": 4304,
|
64 |
+
"model_type": "siglip_vision_model",
|
65 |
+
"num_attention_heads": 16,
|
66 |
+
"num_hidden_layers": 27,
|
67 |
+
"patch_size": 14
|
68 |
+
},
|
69 |
+
"vocab_size": 151666
|
70 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 151643,
|
4 |
+
"eos_token_id": 151645,
|
5 |
+
"transformers_version": "4.42.4"
|
6 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb68d955e4f2100cb9704d9b2560cfee8d3e99b30f2f9bc164c1004ed12708f
|
3 |
+
size 4758426040
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67996f1ccf29e06ef956d82a4c37acafffec223261a3e1eeeee38be8d775a766
|
3 |
+
size 1444788452
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|