Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -1962,4 +1962,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 1962 |
### Framework versions
|
| 1963 |
|
| 1964 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1965 |
- PEFT 0.6.2
|
|
|
|
| 1962 |
### Framework versions
|
| 1963 |
|
| 1964 |
|
| 1965 |
+
- PEFT 0.6.2
|
| 1966 |
+
## Training procedure
|
| 1967 |
+
|
| 1968 |
+
|
| 1969 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 1970 |
+
- load_in_8bit: True
|
| 1971 |
+
- load_in_4bit: False
|
| 1972 |
+
- llm_int8_threshold: 6.0
|
| 1973 |
+
- llm_int8_skip_modules: None
|
| 1974 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 1975 |
+
- llm_int8_has_fp16_weight: False
|
| 1976 |
+
- bnb_4bit_quant_type: fp4
|
| 1977 |
+
- bnb_4bit_use_double_quant: False
|
| 1978 |
+
- bnb_4bit_compute_dtype: float32
|
| 1979 |
+
|
| 1980 |
+
### Framework versions
|
| 1981 |
+
|
| 1982 |
+
|
| 1983 |
- 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 sha256:19370ec825a225c3eacf4c9c5f9750efaed12e1f47db1669d93d8ef3c2bc1f60
|
| 3 |
size 21020682
|