piercemaloney commited on
Commit
dc7db85
1 Parent(s): f6a6640

Upload MllamaForConditionalGeneration

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
3
  "architectures": [
4
  "MllamaForConditionalGeneration"
5
  ],
@@ -30,11 +30,7 @@
30
  "dropout": 0,
31
  "early_stopping": false,
32
  "encoder_no_repeat_ngram_size": 0,
33
- "eos_token_id": [
34
- 128001,
35
- 128008,
36
- 128009
37
- ],
38
  "exponential_decay_length_penalty": null,
39
  "finetuning_task": null,
40
  "forced_bos_token_id": null,
@@ -103,7 +99,7 @@
103
  "vocab_size": 128256
104
  },
105
  "torch_dtype": "bfloat16",
106
- "transformers_version": "4.45.0",
107
  "vision_config": {
108
  "_name_or_path": "",
109
  "add_cross_attention": false,
@@ -130,7 +126,7 @@
130
  "0": "LABEL_0",
131
  "1": "LABEL_1"
132
  },
133
- "image_size": 560,
134
  "initializer_range": 0.02,
135
  "intermediate_layers_indices": [
136
  3,
 
1
  {
2
+ "_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
3
  "architectures": [
4
  "MllamaForConditionalGeneration"
5
  ],
 
30
  "dropout": 0,
31
  "early_stopping": false,
32
  "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": 128001,
 
 
 
 
34
  "exponential_decay_length_penalty": null,
35
  "finetuning_task": null,
36
  "forced_bos_token_id": null,
 
99
  "vocab_size": 128256
100
  },
101
  "torch_dtype": "bfloat16",
102
+ "transformers_version": "4.45.1",
103
  "vision_config": {
104
  "_name_or_path": "",
105
  "add_cross_attention": false,
 
126
  "0": "LABEL_0",
127
  "1": "LABEL_1"
128
  },
129
+ "image_size": 448,
130
  "initializer_range": 0.02,
131
  "intermediate_layers_indices": [
132
  3,
generation_config.json CHANGED
@@ -1,13 +1,7 @@
1
  {
 
2
  "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
  "pad_token_id": 128004,
10
- "temperature": 0.6,
11
- "top_p": 0.9,
12
- "transformers_version": "4.45.0"
13
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
 
 
 
 
 
5
  "pad_token_id": 128004,
6
+ "transformers_version": "4.45.1"
 
 
7
  }
model-00001-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d183d799f0476061adc580ccc0a24abba5ab274d610f02e73aff7576e581118c
3
- size 4992622346
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f9ea8006cc17642463a94a916c5b9ad7907aa02ce4891d42d2095c146de2fa
3
+ size 4988395666
model-00002-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51a7afac7fbc248a8b038709ec3fb5bae4e5588ea84130056c8ed4e5a5144b40
3
- size 4966251712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700ba215225f5e2b16e9d451f2cc9703cfc124ea2a9de8fa8886f7a8911413da
3
+ size 4915919664
model-00003-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24149e6a1922551067d64d78d8a41ac8393e502d6b64f551a4f73bbacbb5bf90
3
  size 4915919704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b06cdc33032dfe5f7a9cf61d9dbe388e2af72e952bda75bf2aedac0bbaadb142
3
  size 4915919704
model-00004-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caf17798db8a5de475bc7580706956032533cd7a9dfb588ad8488229c745bbad
3
  size 4999823980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:806d7a1d87d0a2d45b2f6c42dddc8b8f2b77bcaf45ac085181d0af74f7492909
3
  size 4999823980
model-00005-of-00005.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:656566a9aeee1115ca174c16ea3c51a2839b3a7f14cc349805aa0ef5c7433e7b
3
  size 1465943128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5fefff872f2d7f82ed0498e0b5e7dc10fdd01b051e8be6e41ee3ae4f4fa192d
3
  size 1465943128
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 21340441670
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
@@ -353,10 +353,10 @@
353
  "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
354
  "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
355
  "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
356
- "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
357
- "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
358
  "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
359
- "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
360
  "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
361
  "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
362
  "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 21285882950
4
  },
5
  "weight_map": {
6
  "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
 
353
  "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
354
  "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
355
  "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
356
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
357
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
358
  "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
359
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
360
  "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
361
  "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
362
  "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",