Upload checkpoint trained from Gemma 1.1 2B

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2b-it",
+  "_name_or_path": "google/gemma-1.1-2b-it",
   "architectures": [
     "LlavaGemmaForCausalLM"
   ],
@@ -9,8 +9,8 @@
   "eos_token_id": 1,
   "freeze_mm_mlp_adapter": false,
   "head_dim": 256,
-  "hidden_act": "gelu",
-  "hidden_activation": null,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2048,
   "image_aspect_ratio": "pad",
   "initializer_range": 0.02,
@@ -31,12 +31,11 @@
   "num_key_value_heads": 1,
   "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
-  "tokenizer_model_max_length": 3072,
+  "tokenizer_model_max_length": 4096,
   "tokenizer_padding_side": "right",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.41.0.dev0",
   "tune_mm_mlp_adapter": false,
   "use_cache": true,
   "use_mm_proj": true,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 2,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.41.0.dev0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a879cdd3b2fc6fbfbd151e222acfc7e1d8d845aaff3876a91679e1258b0697
+oid sha256:862efa4d98e8d07baf1e5f1ce46c1d24d953445fe6263bfa56578990f54c5657
 size 4945242264

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66251e77fab9a5bcd12fcbd136a6da22d91cc5055fb5e16b8a0861bcf0ead821
+oid sha256:005624fb8471e7e9b59252d5c7ac9bb64797b5d72205517000d2dc939aecac2d
 size 1274422600

tokenizer_config.json

@@ -1507,7 +1507,7 @@
   "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<eos>",
-  "model_max_length": 3072,
+  "model_max_length": 4096,
   "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1389e5c1499046ef35ff1d499574c6fcb54dfb22378fc45019fc691227d15ffe
-size 6648
+oid sha256:496f2c2ad43e62b2e6084575d2233fe9782bed50acb223e6f68714bfbe1cbdac
+size 6776