Adityyaa
/

Mistral-7b_finetuned_mental_health

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Adityyaa commited on Apr 24

Commit

1a1ce7b

•

1 Parent(s): 8ba6239

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -16,7 +16,7 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "_load_in_4bit": false,
     "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
@@ -26,9 +26,9 @@
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
     "load_in_8bit": false,
-    "quant_method": "bitsandbytes_4bit"
   },
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,

   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "quantization_config": {
+    "_load_in_4bit": true,
     "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
     "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
     "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,