Upload MllamaForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
+  "_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
   "architectures": [
     "MllamaForConditionalGeneration"
   ],
@@ -30,7 +30,11 @@
     "dropout": 0,
     "early_stopping": false,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 128001,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
@@ -126,7 +130,7 @@
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 448,
+    "image_size": 560,
     "initializer_range": 0.02,
     "intermediate_layers_indices": [
       3,

generation_config.json

@@ -1,7 +1,13 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.45.1"
 }

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f9ea8006cc17642463a94a916c5b9ad7907aa02ce4891d42d2095c146de2fa
-size 4988395666
+oid sha256:d183d799f0476061adc580ccc0a24abba5ab274d610f02e73aff7576e581118c
+size 4992622346

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700ba215225f5e2b16e9d451f2cc9703cfc124ea2a9de8fa8886f7a8911413da
-size 4915919664
+oid sha256:51a7afac7fbc248a8b038709ec3fb5bae4e5588ea84130056c8ed4e5a5144b40
+size 4966251712

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06cdc33032dfe5f7a9cf61d9dbe388e2af72e952bda75bf2aedac0bbaadb142
+oid sha256:24149e6a1922551067d64d78d8a41ac8393e502d6b64f551a4f73bbacbb5bf90
 size 4915919704

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:806d7a1d87d0a2d45b2f6c42dddc8b8f2b77bcaf45ac085181d0af74f7492909
+oid sha256:caf17798db8a5de475bc7580706956032533cd7a9dfb588ad8488229c745bbad
 size 4999823980

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fefff872f2d7f82ed0498e0b5e7dc10fdd01b051e8be6e41ee3ae4f4fa192d
+oid sha256:656566a9aeee1115ca174c16ea3c51a2839b3a7f14cc349805aa0ef5c7433e7b
 size 1465943128

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 21285882950
+    "total_size": 21340441670
   },
   "weight_map": {
     "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
@@ -353,10 +353,10 @@
     "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",