Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ai21labs/Jamba-v0.1",
+  "_name_or_path": "Jamba1B/checkpoint-4600",
   "architectures": [
     "JambaForCausalLM"
   ],
@@ -7,9 +7,9 @@
   "attn_layer_offset": 4,
   "attn_layer_period": 8,
   "auto_map": {
-    "AutoConfig": "ai21labs/Jamba-v0.1--configuration_jamba.JambaConfig",
+    "AutoConfig": "configuration_jamba.JambaConfig",
     "AutoModel": "ai21labs/Jamba-v0.1--modeling_jamba.JambaModel",
-    "AutoModelForCausalLM": "ai21labs/Jamba-v0.1--modeling_jamba.JambaForCausalLM",
+    "AutoModelForCausalLM": "modeling_jamba.JambaForCausalLM",
     "AutoModelForSequenceClassification": "ai21labs/Jamba-v0.1--model.JambaForSequenceClassification"
   },
   "bos_token_id": 1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad0e715b769609bac02910d618ad862206b19303a21583bbbfef21337535ec0
+oid sha256:8edf725da48b22f7a144917f83bf749495ecef23fb404b7e47f8d4e9df5f61a7
 size 2039780704