Hugging Face's logo

ravikumar101
/
minicpm_4bit_ravi

Feature Extraction
Transformers
PyTorch
minicpmv
custom_code
4-bit precision
awq
Model card Files Community
minicpm_4bit_ravi
File size: 1,631 Bytes 
030c39a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
 
{
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--openbmb--MiniCPM-Llama3-V-2_5/snapshots/287e3f85192a7c4acf2564fc6bda0637439a9d78",
  "architectures": [
    "MiniCPMV"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_minicpm.MiniCPMVConfig",
    "AutoModel": "modeling_minicpmv.MiniCPMV",
    "AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
  },
  "batch_vision_input": true,
  "bos_token_id": 128000,
  "drop_vision_last_layer": false,
  "eos_token_id": 128001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_size": 448,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "mm_use_im_start_end": true,
  "model_type": "minicpmv",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "patch_size": 14,
  "pretraining_tp": 1,
  "quantization_config": {
    "bits": 4,
    "group_size": 128,
    "quant_method": "awq",
    "version": "gemm",
    "zero_point": true
  },
  "query_num": 96,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "slice_config": {
    "max_slice_nums": 9,
    "model_type": "minicpmv"
  },
  "slice_mode": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.43.2",
  "use_cache": false,
  "version": "2.5",
  "vision_config": {
    "hidden_size": 1152,
    "image_size": 980,
    "intermediate_size": 4304,
    "model_type": "idefics2",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "patch_size": 14
  },
  "vocab_size": 128256
}