Upload OLMoForCausalLM

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "/net/nfs.cirrascale/allennlp/claran/catwalk-models/branched-train-Biology2000-2003-decon-110m",
+  "activation_type": "swiglu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "architectures": [
+    "OLMoForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": null,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "d_model": 768,
+  "embedding_dropout": 0.0,
+  "embedding_size": 50304,
+  "eos_token_id": 50256,
+  "flash_attention": false,
+  "include_bias": true,
+  "init_cutoff_factor": null,
+  "init_device": null,
+  "init_fn": "normal",
+  "init_std": 0.02,
+  "layer_norm_type": "low_precision",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 2048,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "model_type": "olmo",
+  "multi_query_attention": false,
+  "n_heads": 12,
+  "n_layers": 12,
+  "pad_token_id": 50256,
+  "precision": null,
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50280,
+  "weight_tying": true
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a88dfd5eb06cd379c95ea1680461313b108dc0cdf8956d3b95e6fc1e5a7acc4
+size 438344729