Upload folder using huggingface_hub
Browse files- README.md +1 -1
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -199,4 +199,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
-
- PEFT 0.
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.15.0
|
adapter_config.json
CHANGED
|
@@ -10,13 +10,13 @@
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
-
"lora_alpha":
|
| 14 |
"lora_dropout": 0.05,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
-
"r":
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
@@ -27,5 +27,5 @@
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
| 30 |
-
"use_rslora":
|
| 31 |
}
|
|
|
|
| 10 |
"layers_pattern": null,
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
"lora_dropout": 0.05,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
| 17 |
"modules_to_save": null,
|
| 18 |
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
}
|
adapter_model.safetensors
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 sha256:21b3178d6c747660b0ba51c47c81ae02b087763530517cc2d30d0062a0f9c98d
|
| 3 |
+
size 100697728
|
tokenizer_config.json
CHANGED
|
@@ -125,7 +125,7 @@
|
|
| 125 |
"max_seq_length": 131072,
|
| 126 |
"model_max_length": 131072,
|
| 127 |
"pad_token": "<|endoftext|>",
|
| 128 |
-
"padding_side": "
|
| 129 |
"sp_model_kwargs": {},
|
| 130 |
"tokenizer_class": "LlamaTokenizer",
|
| 131 |
"unk_token": "<unk>",
|
|
|
|
| 125 |
"max_seq_length": 131072,
|
| 126 |
"model_max_length": 131072,
|
| 127 |
"pad_token": "<|endoftext|>",
|
| 128 |
+
"padding_side": "left",
|
| 129 |
"sp_model_kwargs": {},
|
| 130 |
"tokenizer_class": "LlamaTokenizer",
|
| 131 |
"unk_token": "<unk>",
|