lunahr
/

SystemGemma2-9b-it

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Piotr Zalewski commited on Aug 11

Commit

4f31f18

•

1 Parent(s): 6d47f47

retrying 32k context

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -15,7 +15,7 @@
   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
   "model_type": "gemma2",
   "num_attention_heads": 16,
   "num_hidden_layers": 42,
@@ -23,8 +23,8 @@
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.0.dev0",

   "hidden_size": 3584,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
   "model_type": "gemma2",
   "num_attention_heads": 16,
   "num_hidden_layers": 42,
   "pad_token_id": 0,
   "query_pre_attn_scalar": 256,
   "rms_norm_eps": 1e-06,
+  "rope_theta": 160000.0,
+  "sliding_window": 32768,
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.42.0.dev0",