Isabelle Cudlitz
commited on
Commit
·
f83f150
1
Parent(s):
dfa1be8
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2124,4 +2124,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2124 |
### Framework versions
|
| 2125 |
|
| 2126 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2127 |
- PEFT 0.6.2
|
|
|
|
| 2124 |
### Framework versions
|
| 2125 |
|
| 2126 |
|
| 2127 |
+
- PEFT 0.6.2
|
| 2128 |
+
## Training procedure
|
| 2129 |
+
|
| 2130 |
+
|
| 2131 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2132 |
+
- load_in_8bit: True
|
| 2133 |
+
- load_in_4bit: False
|
| 2134 |
+
- llm_int8_threshold: 6.0
|
| 2135 |
+
- llm_int8_skip_modules: None
|
| 2136 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2137 |
+
- llm_int8_has_fp16_weight: False
|
| 2138 |
+
- bnb_4bit_quant_type: fp4
|
| 2139 |
+
- bnb_4bit_use_double_quant: False
|
| 2140 |
+
- bnb_4bit_compute_dtype: float32
|
| 2141 |
+
|
| 2142 |
+
### Framework versions
|
| 2143 |
+
|
| 2144 |
+
|
| 2145 |
- 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 sha256:1946a81fcb57b9c6c886a46ec8b0ce068139206b6c953790035db14654b7fbc8
|
| 3 |
size 21020682
|