Upload model
Browse files- README.md +12 -0
- adapter_config.json +2 -2
- adapter_model.bin +2 -2
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 |
|
|
|
201 |
## Training procedure
|
202 |
|
203 |
|
204 |
+
The following `bitsandbytes` quantization config was used during training:
|
205 |
+
- quant_method: bitsandbytes
|
206 |
+
- load_in_8bit: True
|
207 |
+
- load_in_4bit: False
|
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: fp4
|
213 |
+
- bnb_4bit_use_double_quant: False
|
214 |
+
- bnb_4bit_compute_dtype: float32
|
215 |
+
|
216 |
### Framework versions
|
217 |
|
218 |
|
adapter_config.json
CHANGED
@@ -16,8 +16,8 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"
|
21 |
],
|
22 |
"task_type": "SEQ_2_SEQ_LM"
|
23 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"q",
|
20 |
+
"v"
|
21 |
],
|
22 |
"task_type": "SEQ_2_SEQ_LM"
|
23 |
}
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d3726e5c59a8e09bd17c2efec3841ce70e45e7ebd0831c1521fca37d6626779
|
3 |
+
size 18980429
|