Isabelle Cudlitz
commited on
Commit
·
6cf16f1
1
Parent(s):
89d555c
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3042,4 +3042,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3042 |
### Framework versions
|
| 3043 |
|
| 3044 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3045 |
- PEFT 0.6.2
|
|
|
|
| 3042 |
### Framework versions
|
| 3043 |
|
| 3044 |
|
| 3045 |
+
- PEFT 0.6.2
|
| 3046 |
+
## Training procedure
|
| 3047 |
+
|
| 3048 |
+
|
| 3049 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3050 |
+
- load_in_8bit: True
|
| 3051 |
+
- load_in_4bit: False
|
| 3052 |
+
- llm_int8_threshold: 6.0
|
| 3053 |
+
- llm_int8_skip_modules: None
|
| 3054 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3055 |
+
- llm_int8_has_fp16_weight: False
|
| 3056 |
+
- bnb_4bit_quant_type: fp4
|
| 3057 |
+
- bnb_4bit_use_double_quant: False
|
| 3058 |
+
- bnb_4bit_compute_dtype: float32
|
| 3059 |
+
|
| 3060 |
+
### Framework versions
|
| 3061 |
+
|
| 3062 |
+
|
| 3063 |
- 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 sha256:72f69d306db529e69960b98eb148b8bf54dda5bc459faaafff72664da073c32e
|
| 3 |
size 21020682
|