Isabelle Cudlitz
commited on
Commit
·
dfa1be8
1
Parent(s):
5526120
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2106,4 +2106,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2106 |
### Framework versions
|
| 2107 |
|
| 2108 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2109 |
- PEFT 0.6.2
|
|
|
|
| 2106 |
### Framework versions
|
| 2107 |
|
| 2108 |
|
| 2109 |
+
- PEFT 0.6.2
|
| 2110 |
+
## Training procedure
|
| 2111 |
+
|
| 2112 |
+
|
| 2113 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2114 |
+
- load_in_8bit: True
|
| 2115 |
+
- load_in_4bit: False
|
| 2116 |
+
- llm_int8_threshold: 6.0
|
| 2117 |
+
- llm_int8_skip_modules: None
|
| 2118 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2119 |
+
- llm_int8_has_fp16_weight: False
|
| 2120 |
+
- bnb_4bit_quant_type: fp4
|
| 2121 |
+
- bnb_4bit_use_double_quant: False
|
| 2122 |
+
- bnb_4bit_compute_dtype: float32
|
| 2123 |
+
|
| 2124 |
+
### Framework versions
|
| 2125 |
+
|
| 2126 |
+
|
| 2127 |
- 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 sha256:8d147203d7bdb04d70b2e832bcdc524d6f16295946e9fd8e277af43a013f80e9
|
| 3 |
size 21020682
|