Isabelle Cudlitz
commited on
Commit
·
96588b6
1
Parent(s):
89ae39d
Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2070,4 +2070,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2070 |
### Framework versions
|
| 2071 |
|
| 2072 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2073 |
- PEFT 0.6.2
|
|
|
|
| 2070 |
### Framework versions
|
| 2071 |
|
| 2072 |
|
| 2073 |
+
- PEFT 0.6.2
|
| 2074 |
+
## Training procedure
|
| 2075 |
+
|
| 2076 |
+
|
| 2077 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2078 |
+
- load_in_8bit: True
|
| 2079 |
+
- load_in_4bit: False
|
| 2080 |
+
- llm_int8_threshold: 6.0
|
| 2081 |
+
- llm_int8_skip_modules: None
|
| 2082 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2083 |
+
- llm_int8_has_fp16_weight: False
|
| 2084 |
+
- bnb_4bit_quant_type: fp4
|
| 2085 |
+
- bnb_4bit_use_double_quant: False
|
| 2086 |
+
- bnb_4bit_compute_dtype: float32
|
| 2087 |
+
|
| 2088 |
+
### Framework versions
|
| 2089 |
+
|
| 2090 |
+
|
| 2091 |
- 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:b29823bcde11e73fecc837611c602feb5af60ae955ec81c0145e7b7dc337abee
|
| 3 |
size 21020682
|