Isabelle Cudlitz commited on
Commit ·
89d555c
1
Parent(s): faf938e
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3024,4 +3024,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3024 |
### Framework versions
|
| 3025 |
|
| 3026 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3027 |
- PEFT 0.6.2
|
|
|
|
| 3024 |
### Framework versions
|
| 3025 |
|
| 3026 |
|
| 3027 |
+
- PEFT 0.6.2
|
| 3028 |
+
## Training procedure
|
| 3029 |
+
|
| 3030 |
+
|
| 3031 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 3032 |
+
- load_in_8bit: True
|
| 3033 |
+
- load_in_4bit: False
|
| 3034 |
+
- llm_int8_threshold: 6.0
|
| 3035 |
+
- llm_int8_skip_modules: None
|
| 3036 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 3037 |
+
- llm_int8_has_fp16_weight: False
|
| 3038 |
+
- bnb_4bit_quant_type: fp4
|
| 3039 |
+
- bnb_4bit_use_double_quant: False
|
| 3040 |
+
- bnb_4bit_compute_dtype: float32
|
| 3041 |
+
|
| 3042 |
+
### Framework versions
|
| 3043 |
+
|
| 3044 |
+
|
| 3045 |
- 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 sha256:04df420e4816d1593b254d94d3fd04ea12f98c50edee2955ba80e08186aaebe2
|
| 3 |
size 21020682
|