JohnConnor123
/

Qwen2.5-0.5B-Instruct-BNB-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

JohnConnor123 commited on 9 days ago

Commit

ade743b

·

verified ·

1 Parent(s): 519618f

Upload Qwen2ForCausalLM

Files changed (2) hide show

config.json +5 -5
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -17,17 +17,17 @@
   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "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": 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,
     "quant_method": "bitsandbytes"
   },

   "num_hidden_layers": 24,
   "num_key_value_heads": 2,
   "quantization_config": {
+    "_load_in_4bit": false,
     "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
     "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": false,
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6ed98084afb0497d9075a82ab17fdfc0b5d99fb6b37d8f761463e67c100f45
-size 457346831

 version https://git-lfs.github.com/spec/v1
+oid sha256:4754fcd539fe8382bcc8c4245237bb16cf3f804c622a56fc530916947202ebd1
+size 473806824