zainabkhan
/

phi2

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions

zainabkhan commited on Apr 25, 2024

Commit

db70694

·

verified ·

1 Parent(s): 67c5a4c

Upload PhiForCausalLM

Files changed (2) hide show

config.json +2 -2
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -27,7 +27,7 @@
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,
@@ -43,7 +43,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0.dev0",
   "use_cache": false,
   "vocab_size": 51200

   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
   "use_cache": false,
   "vocab_size": 51200

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee7ab92c1b48735ca7e933cdce08f6514be4cc61c9621e8791d7aa618f8e0d4
-size 2132377992

 version https://git-lfs.github.com/spec/v1
+oid sha256:4548e768d559824b207bfe2417ba9ba274025d6c6f1d3a73e9782b4d8598d7ed
+size 2845514624