fix

README.md

@@ -1,3 +0,0 @@
----
-license: bigscience-openrail-m
----

config.json

@@ -1,21 +1,48 @@
 {
+  "additional_vocab_size": 2,
+  "alpha_initializer": "ones",
+  "alpha_type": "vector",
+  "alphas_initializer_range": 0.0,
   "architectures": [
-    "AtumForCausalLM"
+    "VLlamaForCausalLM"
   ],
-  "bos_token_id": 0,
-  "eos_token_id": 1,
+  "bos_token_id": 1,
+  "cross_layer_activation_function": "swiglu",
+  "cross_layer_interval": 1,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "ffn_dim": 64,
+  "freeze_lm_head": false,
+  "freeze_text_layers": true,
+  "freeze_text_module_exceptions": [],
+  "freeze_vision_layers": true,
+  "freeze_vision_module_exceptions": [],
   "hidden_act": "silu",
   "hidden_size": 16,
   "initializer_range": 0.02,
-  "intermediate_size": 64,
-  "model_type": "atum",
+  "intermediate_size": 11008,
+  "max_new_tokens": 100,
+  "max_position_embeddings": 128,
+  "model_type": "vllama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "pad_token_id": -1,
+  "pad_token_id": 0,
+  "qk_layer_norms": false,
+  "qk_layer_norms_perceiver": false,
+  "resampler_depth": 2,
+  "resampler_head_dim": 8,
+  "resampler_n_heads": 2,
+  "resampler_n_latents": 16,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.27.0.dev0",
   "use_cache": true,
-  "vocab_size": 32000
+  "use_resampler": true,
+  "vision_embed_dim": 32,
+  "vision_image_size": 30,
+  "vision_model_name": "hf-internal-testing/tiny-random-clip",
+  "vision_model_params": "{}",
+  "vocab_size": 32000,
+  "word_embed_proj_dim": 16
 }

generation_config.json

@@ -1,7 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": -1,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_new_tokens": 100,
+  "pad_token_id": 0,
   "transformers_version": "4.27.0.dev0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead8d18a1b6d6948761f23fec1647cda5b6af3dbdd23a30769824ab26f4c30b8
-size 2071008
+oid sha256:b6f5de05e77b318f3a80f79e1a8d6b1eda26841ecfd9c0afc4c38a2d14b4e6a5
+size 6467421

special_tokens_map.json

@@ -1 +0,0 @@
-{}

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

tokenizer_config.json

@@ -1,7 +0,0 @@
-{
-  "bos_token": "",
-  "eos_token": "",
-  "model_max_length": 1000000000000000019884624838656,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": ""
-}