ftanguy
/

MNLP_M3_quantized_model

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

ftanguy commited on Jun 10

Commit

f6eda05

·

verified ·

1 Parent(s): b217346

Upload Qwen3ForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -52,7 +52,7 @@
     "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,

     "_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,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fa213dbe8c09e525309ed9a346e28b1b6a2a9c89e82d7a6b199a2fed85ca57
 size 538883409

 version https://git-lfs.github.com/spec/v1
+oid sha256:ffe7b33f8c2434319b80eeae4adeea92b686976fd876f3bb593ed6c14688d621
 size 538883409