Upload RWForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "_name_or_path": "OpenAssistant/falcon-7b-sft-mix-2000",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -7,12 +7,12 @@
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
-    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
-    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
-    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
-    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
+    "AutoConfig": "OpenAssistant/falcon-7b-sft-mix-2000--configuration_RW.RWConfig",
+    "AutoModel": "OpenAssistant/falcon-7b-sft-mix-2000--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "OpenAssistant/falcon-7b-sft-mix-2000--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "OpenAssistant/falcon-7b-sft-mix-2000--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "OpenAssistant/falcon-7b-sft-mix-2000--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "OpenAssistant/falcon-7b-sft-mix-2000--modelling_RW.RWForTokenClassification"
   },
   "bias": false,
   "bos_token_id": 11,
@@ -35,5 +35,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
   "use_cache": false,
-  "vocab_size": 65024
+  "vocab_size": 65040
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a6218e7fa3523a1e2df48e1625e1172c622e07e772af97cc7f03b5e36a95b3
-size 8070284393
+oid sha256:7e864e663f046de39dc63e765c065a645e9f68be8ef36fcfc79c226d25e07559
+size 8331670741