Upload model
Browse files- README.md +18 -0
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -3996,4 +3996,22 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 3996 |
### Framework versions
|
| 3997 |
|
| 3998 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3999 |
- PEFT 0.6.2
|
|
|
|
| 3996 |
### Framework versions
|
| 3997 |
|
| 3998 |
|
| 3999 |
+
- PEFT 0.6.2
|
| 4000 |
+
## Training procedure
|
| 4001 |
+
|
| 4002 |
+
|
| 4003 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 4004 |
+
- load_in_8bit: True
|
| 4005 |
+
- load_in_4bit: False
|
| 4006 |
+
- llm_int8_threshold: 6.0
|
| 4007 |
+
- llm_int8_skip_modules: None
|
| 4008 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 4009 |
+
- llm_int8_has_fp16_weight: False
|
| 4010 |
+
- bnb_4bit_quant_type: fp4
|
| 4011 |
+
- bnb_4bit_use_double_quant: False
|
| 4012 |
+
- bnb_4bit_compute_dtype: float32
|
| 4013 |
+
|
| 4014 |
+
### Framework versions
|
| 4015 |
+
|
| 4016 |
+
|
| 4017 |
- 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:ac79a3bcf4ad20b81a8fa690745bf59beb8a22cf38d18ddf641fd451ac55b6da
|
| 3 |
size 21020682
|