ramdhanfirdaus commited on
Commit
10074ca
1 Parent(s): da4fda1

Upload model

Browse files
Files changed (2) hide show
  1. README.md +24 -0
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -201,6 +201,18 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
201
  ## Training procedure
202
 
203
 
 
 
 
 
 
 
 
 
 
 
 
 
204
  ### Framework versions
205
 
206
 
@@ -208,6 +220,18 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
208
  ## Training procedure
209
 
210
 
 
 
 
 
 
 
 
 
 
 
 
 
211
  ### Framework versions
212
 
213
 
 
201
  ## Training procedure
202
 
203
 
204
+ The following `bitsandbytes` quantization config was used during training:
205
+ - quant_method: bitsandbytes
206
+ - load_in_8bit: False
207
+ - load_in_4bit: True
208
+ - llm_int8_threshold: 6.0
209
+ - llm_int8_skip_modules: None
210
+ - llm_int8_enable_fp32_cpu_offload: False
211
+ - llm_int8_has_fp16_weight: False
212
+ - bnb_4bit_quant_type: nf4
213
+ - bnb_4bit_use_double_quant: True
214
+ - bnb_4bit_compute_dtype: float16
215
+
216
  ### Framework versions
217
 
218
 
 
220
  ## Training procedure
221
 
222
 
223
+ The following `bitsandbytes` quantization config was used during training:
224
+ - quant_method: bitsandbytes
225
+ - load_in_8bit: False
226
+ - load_in_4bit: True
227
+ - llm_int8_threshold: 6.0
228
+ - llm_int8_skip_modules: None
229
+ - llm_int8_enable_fp32_cpu_offload: False
230
+ - llm_int8_has_fp16_weight: False
231
+ - bnb_4bit_quant_type: nf4
232
+ - bnb_4bit_use_double_quant: True
233
+ - bnb_4bit_compute_dtype: float16
234
+
235
  ### Framework versions
236
 
237
 
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc68cfd27343b2a091337733530cd471e3514bb8952658da53d09396fff40aad
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ee02b3aa5d63370ea922c222e07dc9198d3d121ff19848f7caa93176fc2c81
3
  size 50338848