Update config.json

config.json

@@ -1,14 +1,20 @@
 {
+  "_name_or_path": "tiiuae/falcon-7b-instruct",
   "alibi": false,
   "apply_residual_connection_post_layernorm": false,
+  "trust_remote_code": true,
   "architectures": [
     "RWForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "configuration_RW.RWConfig",
-    "AutoModelForCausalLM": "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"
   },
-  "attention_dropout": 0.0,
   "bias": false,
   "bos_token_id": 11,
   "eos_token_id": 11,
@@ -21,8 +27,19 @@
   "n_head": 71,
   "n_layer": 32,
   "parallel_attn": true,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false
+  },
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.27.4",
-  "use_cache": true,
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": false,
   "vocab_size": 65024
-}
+}