Model quantized to 8 bits

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
+  "_name_or_path": "vilsonrodrigues/falcon-7b-sharded",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -7,8 +7,12 @@
   ],
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "tiiuae/falcon-7b-instruct--configuration_RW.RWConfig",
-    "AutoModelForCausalLM": "tiiuae/falcon-7b-instruct--modelling_RW.RWForCausalLM"
+    "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"
   },
   "bias": false,
   "bos_token_id": 11,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b864a4b0fe1459bc984eb5f88348587057556fcb4b561833bc338ea0fee70c3b
-size 7221688297
+oid sha256:e03bc362234793a585598ac95a32973a1e3fcdc00cf836aad47cdecbfb45ba43
+size 7217556969