Isabelle Cudlitz
commited on
Commit
·
3930236
1
Parent(s):
d24fb43
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2934,4 +2934,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2934 |
### Framework versions
|
| 2935 |
|
| 2936 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2937 |
- PEFT 0.6.2
|
|
|
|
| 2934 |
### Framework versions
|
| 2935 |
|
| 2936 |
|
| 2937 |
+
- PEFT 0.6.2
|
| 2938 |
+
## Training procedure
|
| 2939 |
+
|
| 2940 |
+
|
| 2941 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2942 |
+
- load_in_8bit: True
|
| 2943 |
+
- load_in_4bit: False
|
| 2944 |
+
- llm_int8_threshold: 6.0
|
| 2945 |
+
- llm_int8_skip_modules: None
|
| 2946 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2947 |
+
- llm_int8_has_fp16_weight: False
|
| 2948 |
+
- bnb_4bit_quant_type: fp4
|
| 2949 |
+
- bnb_4bit_use_double_quant: False
|
| 2950 |
+
- bnb_4bit_compute_dtype: float32
|
| 2951 |
+
|
| 2952 |
+
### Framework versions
|
| 2953 |
+
|
| 2954 |
+
|
| 2955 |
- PEFT 0.6.2
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21020682
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0caf1302ebf375e5b18edfc5fed3161cdc07deac9ec8aeb3efc91002b3b40573
|
| 3 |
size 21020682
|