Upload GemmaForCausalLM

README.md

@@ -1,12 +1,12 @@
 ---
+datasets:
+- allenai/dolma
 language:
 - en
-tags:
-- causal-lm
 library_name: transformers
 license: apache-2.0
-datasets:
-- allenai/dolma
+tags:
+- causal-lm
 ---
 
 ## Model Details

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "final_logit_softcapping": null,
+  "head_dim": 128,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "max_position_embeddings": 2048,
+  "model_type": "gemma",
+  "num_attention_heads": 10,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 5,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b4b7c25af7a395d305218f2a647c718a00df6c746f249dbc0529c957f1bd17
+size 4054468192