Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2142,4 +2142,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2142 |
### Framework versions
|
| 2143 |
|
| 2144 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2145 |
- PEFT 0.6.2
|
|
|
|
| 2142 |
### Framework versions
|
| 2143 |
|
| 2144 |
|
| 2145 |
+
- PEFT 0.6.2
|
| 2146 |
+
## Training procedure
|
| 2147 |
+
|
| 2148 |
+
|
| 2149 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2150 |
+
- load_in_8bit: True
|
| 2151 |
+
- load_in_4bit: False
|
| 2152 |
+
- llm_int8_threshold: 6.0
|
| 2153 |
+
- llm_int8_skip_modules: None
|
| 2154 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2155 |
+
- llm_int8_has_fp16_weight: False
|
| 2156 |
+
- bnb_4bit_quant_type: fp4
|
| 2157 |
+
- bnb_4bit_use_double_quant: False
|
| 2158 |
+
- bnb_4bit_compute_dtype: float32
|
| 2159 |
+
|
| 2160 |
+
### Framework versions
|
| 2161 |
+
|
| 2162 |
+
|
| 2163 |
- 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 sha256:327335ea716e6124f13397d1d4f1ad7979465bf4d306f0568410125a5a6ce24a
|
| 3 |
size 21020682
|