Upload MolmoForCausalLM

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "allenai/Molmo-7B-D-0924",
+  "architectures": [
+    "MolmoForCausalLM"
+  ],
+  "attention_layer_norm": false,
+  "auto_map": {
+    "AutoConfig": "config_molmo.MolmoConfig",
+    "AutoModelForCausalLM": "allenai/Molmo-7B-D-0924--modeling_molmo.MolmoForCausalLM"
+  },
+  "clip_qkv": null,
+  "embedding_size": 152064,
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 37888,
+  "layer_norm_eps": 1e-06,
+  "layer_norm_type": "rms",
+  "max_position_embeddings": 4096,
+  "model_type": "molmo",
+  "norm_after": false,
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "qkv_bias": true,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "use_position_ids": true,
+  "vocab_size": 152064,
+  "weight_tying": false
+}

config_molmo.py

@@ -0,0 +1,60 @@
+from typing import List
+
+from transformers import PretrainedConfig, AutoTokenizer
+
+
+class MolmoConfig(PretrainedConfig):
+    model_type = "molmo"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=50304,
+        embedding_size=50304,
+        hidden_size=4096,
+        intermediate_size=11008,
+        num_hidden_layers=32,
+        num_attention_heads=32,
+        num_key_value_heads=None,
+        max_position_embeddings=2048,
+        initializer_range=0.02,
+        use_cache=True,
+        layer_norm_eps: float = 1e-5,
+        rope_theta=10000.0,
+        clip_qkv=None,
+        qkv_bias: bool = False,
+        weight_tying: bool = False,
+        use_position_ids: bool=True,
+        tie_word_embeddings: bool=True,
+        attention_layer_norm: bool=False,
+        norm_after: bool = False,
+        layer_norm_type: str="rms",
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.embedding_size = embedding_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.layer_norm_eps = layer_norm_eps
+        self.weight_tying = weight_tying
+        self.use_position_ids = use_position_ids
+        self.attention_layer_norm = attention_layer_norm
+        self.num_key_value_heads = num_key_value_heads
+        self.initializer_range = initializer_range
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.clip_qkv = clip_qkv
+        self.qkv_bias = qkv_bias
+        self.norm_after = norm_after
+        self.tie_word_embeddings = tie_word_embeddings
+        self.layer_norm_type = layer_norm_type
+
+        super().__init__(
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+MolmoConfig.register_for_auto_class()

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.44.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8f08d55da7152a5d2cfdbcecab6862e5c27d6b0e0eaf931675bf4caf9e8808c
+size 4998427912

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c2f47912826c850d5387d8ef60990d9232408cd8302cb553ac3fefe98a0d9ee
+size 2943573752