Commit
·
aec51cc
1
Parent(s):
a6e5196
Upload trained [Ludwig](https://ludwig.ai/latest/) model weights
Browse files- README.md +1 -22
- adapter_config.json +3 -0
- adapter_model.bin +2 -2
- adapter_model.safetensors +3 -0
README.md
CHANGED
@@ -201,26 +201,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
201 |
|
202 |
## Training procedure
|
203 |
|
204 |
-
|
205 |
-
The following `bitsandbytes` quantization config was used during training:
|
206 |
-
- quant_method: bitsandbytes
|
207 |
-
- load_in_8bit: False
|
208 |
-
- load_in_4bit: True
|
209 |
-
- llm_int8_threshold: 6.0
|
210 |
-
- llm_int8_skip_modules: None
|
211 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
212 |
-
- llm_int8_has_fp16_weight: False
|
213 |
-
- bnb_4bit_quant_type: nf4
|
214 |
-
- bnb_4bit_use_double_quant: True
|
215 |
-
- bnb_4bit_compute_dtype: float16
|
216 |
-
|
217 |
-
### Framework versions
|
218 |
-
|
219 |
-
|
220 |
-
- PEFT 0.6.2
|
221 |
-
## Training procedure
|
222 |
-
|
223 |
-
|
224 |
The following `bitsandbytes` quantization config was used during training:
|
225 |
- quant_method: bitsandbytes
|
226 |
- load_in_8bit: False
|
@@ -235,5 +215,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
235 |
|
236 |
### Framework versions
|
237 |
|
238 |
-
|
239 |
-
- PEFT 0.6.2
|
|
|
201 |
|
202 |
## Training procedure
|
203 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
204 |
The following `bitsandbytes` quantization config was used during training:
|
205 |
- quant_method: bitsandbytes
|
206 |
- load_in_8bit: False
|
|
|
215 |
|
216 |
### Framework versions
|
217 |
|
218 |
+
- PEFT 0.7.0
|
|
adapter_config.json
CHANGED
@@ -8,8 +8,11 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.05,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 8,
|
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
"lora_alpha": 16,
|
13 |
"lora_dropout": 0.05,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 8,
|
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85113bd3c2f642abccaa0c52561a62fbfdf7750edd2ff01eb5b21efe24fec53
|
3 |
+
size 13648432
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85113bd3c2f642abccaa0c52561a62fbfdf7750edd2ff01eb5b21efe24fec53
|
3 |
+
size 13648432
|