Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -2088,4 +2088,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 2088 |
### Framework versions
|
| 2089 |
|
| 2090 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2091 |
- PEFT 0.6.2
|
|
|
|
| 2088 |
### Framework versions
|
| 2089 |
|
| 2090 |
|
| 2091 |
+
- PEFT 0.6.2
|
| 2092 |
+
## Training procedure
|
| 2093 |
+
|
| 2094 |
+
|
| 2095 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 2096 |
+
- load_in_8bit: True
|
| 2097 |
+
- load_in_4bit: False
|
| 2098 |
+
- llm_int8_threshold: 6.0
|
| 2099 |
+
- llm_int8_skip_modules: None
|
| 2100 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 2101 |
+
- llm_int8_has_fp16_weight: False
|
| 2102 |
+
- bnb_4bit_quant_type: fp4
|
| 2103 |
+
- bnb_4bit_use_double_quant: False
|
| 2104 |
+
- bnb_4bit_compute_dtype: float32
|
| 2105 |
+
|
| 2106 |
+
### Framework versions
|
| 2107 |
+
|
| 2108 |
+
|
| 2109 |
- 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:fc5f710bdfdbc654dccc1bc27b845b155bfaa4659c66fc8a0ef2e40972e88413
|
| 3 |
size 21020682
|