A2Amir commited on
Commit
bdd9538
·
verified ·
1 Parent(s): f624928

Upload IdeficsForVisionText2Text

Browse files
README.md CHANGED
@@ -1,6 +1,8 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
7
 
8
  # Model Card for Model ID
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceM4/idefics-9b",
3
+ "additional_vocab_size": 2,
4
+ "alpha_initializer": "zeros",
5
+ "alpha_type": "float",
6
+ "alphas_initializer_range": 0.0,
7
+ "architectures": [
8
+ "IdeficsForVisionText2Text"
9
+ ],
10
+ "bos_token_id": 1,
11
+ "cross_layer_activation_function": "swiglu",
12
+ "cross_layer_interval": 4,
13
+ "dropout": 0.0,
14
+ "eos_token_id": 2,
15
+ "freeze_lm_head": false,
16
+ "freeze_text_layers": false,
17
+ "freeze_text_module_exceptions": [],
18
+ "freeze_vision_layers": false,
19
+ "freeze_vision_module_exceptions": [],
20
+ "hidden_act": "silu",
21
+ "hidden_size": 4096,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 11008,
24
+ "max_position_embeddings": 2048,
25
+ "max_sequence_length": 2048,
26
+ "model_type": "idefics",
27
+ "num_attention_heads": 32,
28
+ "num_hidden_layers": 32,
29
+ "pad_token_id": 0,
30
+ "perceiver_config": {
31
+ "model_type": "idefics",
32
+ "qk_layer_norms_perceiver": true
33
+ },
34
+ "qk_layer_norms": true,
35
+ "quantization_config": {
36
+ "_load_in_4bit": true,
37
+ "_load_in_8bit": false,
38
+ "bnb_4bit_compute_dtype": "float16",
39
+ "bnb_4bit_quant_storage": "uint8",
40
+ "bnb_4bit_quant_type": "nf4",
41
+ "bnb_4bit_use_double_quant": true,
42
+ "llm_int8_enable_fp32_cpu_offload": false,
43
+ "llm_int8_has_fp16_weight": false,
44
+ "llm_int8_skip_modules": [
45
+ "lm_head",
46
+ "embed_tokens"
47
+ ],
48
+ "llm_int8_threshold": 6.0,
49
+ "load_in_4bit": true,
50
+ "load_in_8bit": false,
51
+ "quant_method": "bitsandbytes"
52
+ },
53
+ "rms_norm_eps": 1e-06,
54
+ "tie_word_embeddings": false,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.44.2",
57
+ "use_cache": true,
58
+ "use_resampler": true,
59
+ "vision_config": {
60
+ "embed_dim": 1280,
61
+ "model_type": "idefics"
62
+ },
63
+ "vocab_size": 32000
64
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.2"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ac34faa75742418cbc33c952ca48bece49ce6d79f1d4ef1453fa0a8f7a49c9
3
+ size 4981248757
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12840fb24bf81be24bc27330949379c1cc0d6e29c2a6f78c7d46a8e4d601118d
3
+ size 863090189
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff