Upload model
Browse files- README.md +19 -0
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -97,4 +97,23 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 97 |
### Framework versions
|
| 98 |
|
| 99 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
- PEFT 0.6.2
|
|
|
|
| 97 |
### Framework versions
|
| 98 |
|
| 99 |
|
| 100 |
+
- PEFT 0.6.2
|
| 101 |
+
## Training procedure
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 105 |
+
- quant_method: bitsandbytes
|
| 106 |
+
- load_in_8bit: False
|
| 107 |
+
- load_in_4bit: True
|
| 108 |
+
- llm_int8_threshold: 6.0
|
| 109 |
+
- llm_int8_skip_modules: None
|
| 110 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 111 |
+
- llm_int8_has_fp16_weight: False
|
| 112 |
+
- bnb_4bit_quant_type: nf4
|
| 113 |
+
- bnb_4bit_use_double_quant: False
|
| 114 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 115 |
+
|
| 116 |
+
### Framework versions
|
| 117 |
+
|
| 118 |
+
|
| 119 |
- PEFT 0.6.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 75518144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f25dc485a7cb943a1854230ef49a6f8db6472502e949870494b3b4b62c0b4cb8
|
| 3 |
size 75518144
|