Try to fixup causal lm

config.json

@@ -1,7 +1,7 @@
 {
   "alibi": false,
   "architectures": [
-    "FalconModel"
+    "FalconForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bias": false,
@@ -11,6 +11,7 @@
   "hidden_size": 256,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
   "model_type": "falcon",
   "multi_query": true,
   "new_decoder_architecture": true,
@@ -18,8 +19,10 @@
   "num_hidden_layers": 5,
   "num_kv_heads": 2,
   "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.34.0.dev0",
   "use_cache": true,
   "vocab_size": 1024
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0401b0bba6dd4f646231630ebb2a000afc4ca2d77b4ff96c841834ac906753f8
-size 15501938
+oid sha256:1248a031fea1cea953b8992e6ec7e595657e8bbbc9c39f2796d788a1be000bc1
+size 15502514