update model with latest tokenizer

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "tiny-random-vllama-clip",
   "additional_vocab_size": 2,
   "alpha_initializer": "ones",
   "alpha_type": "vector",
@@ -24,7 +23,7 @@
   "intermediate_size": 11008,
   "max_new_tokens": 100,
   "max_position_embeddings": 128,
-  "model_type": "llama",
+  "model_type": "vllama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "pad_token_id": 0,
@@ -36,8 +35,8 @@
   "resampler_n_latents": 16,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
   "use_resampler": true,
   "vision_embed_dim": 32,

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "max_new_tokens": 100,
   "pad_token_id": 0,
-  "transformers_version": "4.28.0.dev0"
+  "transformers_version": "4.27.0.dev0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b12743cfed7632ce36846850750c4c874dba173638e1d85c1d1e03b74c1610
-size 12878457
+oid sha256:b6f5de05e77b318f3a80f79e1a8d6b1eda26841ecfd9c0afc4c38a2d14b4e6a5
+size 6467421