Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1926,4 +1926,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1926 |
### Framework versions
|
| 1927 |
|
| 1928 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1929 |
- PEFT 0.6.2
|
|
|
|
| 1926 |
### Framework versions
|
| 1927 |
|
| 1928 |
|
| 1929 |
+
- PEFT 0.6.2
|
| 1930 |
+
## Training procedure
|
| 1931 |
+
|
| 1932 |
+
|
| 1933 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1934 |
+
- load_in_8bit: True
|
| 1935 |
+
- load_in_4bit: False
|
| 1936 |
+
- llm_int8_threshold: 6.0
|
| 1937 |
+
- llm_int8_skip_modules: None
|
| 1938 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1939 |
+
- llm_int8_has_fp16_weight: False
|
| 1940 |
+
- bnb_4bit_quant_type: fp4
|
| 1941 |
+
- bnb_4bit_use_double_quant: False
|
| 1942 |
+
- bnb_4bit_compute_dtype: float32
|
| 1943 |
+
|
| 1944 |
+
### Framework versions
|
| 1945 |
+
|
| 1946 |
+
|
| 1947 |
- 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 sha256:82ea710bfcf53391738432b09afea05d3eb9d8844b6ce30efedf77177305ee2d
|
| 3 |
size 21020682
|