John6666
/

llama-joycaption-alpha-two-hf-llava-nf4

Image-Text-to-Text

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

John6666 commited on Oct 13

Commit

ee4c79e

•

1 Parent(s): 1e0b27a

Upload 8 files

Files changed (2) hide show

config.json +1 -1
model-00001-of-00002.safetensors +2 -2

config.json CHANGED Viewed

@@ -12,7 +12,7 @@
     "_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,

     "_load_in_4bit": true,
     "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e061ba102f9521efa2c3eb12237a0d8e927ceb02302a36e9c089981c7056a26
-size 4893276740

 version https://git-lfs.github.com/spec/v1
+oid sha256:d25ac0c7ab918fcad0f4cda6d6e80a282e0f666816d0175fad60b9717dbc9640
+size 4893277524