iagoalves
/

Qwen2.5-1.5B-bnb-4bit_lorav1

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

iagoalves commited on Nov 27, 2024

Commit

11e23da

·

verified ·

1 Parent(s): d5819a4

Upload Qwen2ForCausalLM

Files changed (2) hide show

config.json +8 -8
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -17,18 +17,18 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
   "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "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": 200.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-06,

   "num_hidden_layers": 28,
   "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"
   },
   "rms_norm_eps": 1e-06,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ba2b9d6f60b8742337e9c86dbdfa85952139bae3f5f5f4d6b0397f199014b6
-size 2246931092

 version https://git-lfs.github.com/spec/v1
+oid sha256:e62a0b58bfd291a9809ab89c28296b10bd6b0ad08459911abc466b1cf264058b
+size 1610369128