Upload folder using huggingface_hub
Browse files- README.md +1 -0
- adapter_config.json +15 -16
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -199,5 +199,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
|
|
|
| 202 |
- PEFT 0.12.0
|
| 203 |
- PEFT 0.13.2
|
|
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
| 202 |
+
- PEFT 0.15.0
|
| 203 |
- PEFT 0.12.0
|
| 204 |
- PEFT 0.13.2
|
adapter_config.json
CHANGED
|
@@ -3,6 +3,9 @@
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 5 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
| 6 |
"fan_in_fan_out": false,
|
| 7 |
"inference_mode": true,
|
| 8 |
"init_lora_weights": true,
|
|
@@ -11,6 +14,7 @@
|
|
| 11 |
"layers_to_transform": null,
|
| 12 |
"loftq_config": {},
|
| 13 |
"lora_alpha": 64,
|
|
|
|
| 14 |
"lora_dropout": 0.128426644097236,
|
| 15 |
"megatron_config": null,
|
| 16 |
"megatron_core": "megatron.core",
|
|
@@ -20,28 +24,23 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"cross_attention.k_proj",
|
| 24 |
-
"gate_proj",
|
| 25 |
-
"gate_up_proj",
|
| 26 |
-
"q_proj",
|
| 27 |
-
"fc1",
|
| 28 |
-
"encoder_attn.q_proj",
|
| 29 |
-
"cross_attention.q_proj",
|
| 30 |
-
"cross_attention.v_proj",
|
| 31 |
-
"lm_head",
|
| 32 |
"v_proj",
|
| 33 |
"fc2",
|
| 34 |
-
"up_proj",
|
| 35 |
-
"k_proj",
|
| 36 |
-
"word_embeddings",
|
| 37 |
"down_proj",
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"position_embeddings",
|
| 41 |
"qkv_proj",
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 45 |
"use_dora": false,
|
| 46 |
"use_rslora": true
|
| 47 |
}
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 5 |
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": true,
|
|
|
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
"lora_alpha": 64,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
"lora_dropout": 0.128426644097236,
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
"v_proj",
|
| 28 |
"fc2",
|
|
|
|
|
|
|
|
|
|
| 29 |
"down_proj",
|
| 30 |
+
"fc1",
|
| 31 |
+
"word_embeddings",
|
|
|
|
| 32 |
"qkv_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"up_proj",
|
| 35 |
+
"position_embeddings",
|
| 36 |
+
"gate_up_proj",
|
| 37 |
+
"lm_head",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"o_proj",
|
| 40 |
+
"gate_proj"
|
| 41 |
],
|
| 42 |
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
"use_dora": false,
|
| 45 |
"use_rslora": true
|
| 46 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2351485824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2910008f4ee8997fd4d5777a4ef4d325431b432d80e7e1cbc624e27f23316fe
|
| 3 |
size 2351485824
|