Isabelle Cudlitz commited on
Commit
fe832ec
·
1 Parent(s): d3c8e1e

Upload model

Browse files
Files changed (2) hide show
  1. README.md +18 -0
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -1278,4 +1278,22 @@ The following `bitsandbytes` quantization config was used during training:
1278
  ### Framework versions
1279
 
1280
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1281
  - PEFT 0.6.2
 
1278
  ### Framework versions
1279
 
1280
 
1281
+ - PEFT 0.6.2
1282
+ ## Training procedure
1283
+
1284
+
1285
+ The following `bitsandbytes` quantization config was used during training:
1286
+ - load_in_8bit: False
1287
+ - load_in_4bit: True
1288
+ - llm_int8_threshold: 6.0
1289
+ - llm_int8_skip_modules: None
1290
+ - llm_int8_enable_fp32_cpu_offload: False
1291
+ - llm_int8_has_fp16_weight: False
1292
+ - bnb_4bit_quant_type: fp4
1293
+ - bnb_4bit_use_double_quant: True
1294
+ - bnb_4bit_compute_dtype: float32
1295
+
1296
+ ### Framework versions
1297
+
1298
+
1299
  - PEFT 0.6.2
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee3fe6ac1d428ce4e0385cec829a1e29b6f6c4208fe776b18a3ff2a8466072eb
3
  size 21020682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c466e6f74a4bc6f089286b47e1702424c480b02ac9a663a752d72cf62ec23e78
3
  size 21020682