Upload checkpoint-63/adapter_config.json with huggingface_hub
Browse files
checkpoint-63/adapter_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "GptOssForCausalLM",
|
| 5 |
+
"parent_library": "transformers.models.gpt_oss.modeling_gpt_oss"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "openai/gpt-oss-20b",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"corda_config": null,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 16,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.0,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"qalora_group_size": 16,
|
| 27 |
+
"r": 8,
|
| 28 |
+
"rank_pattern": {},
|
| 29 |
+
"revision": null,
|
| 30 |
+
"target_modules": [
|
| 31 |
+
"k_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"q_proj"
|
| 35 |
+
],
|
| 36 |
+
"target_parameters": [
|
| 37 |
+
"7.mlp.experts.gate_up_proj",
|
| 38 |
+
"7.mlp.experts.down_proj",
|
| 39 |
+
"15.mlp.experts.gate_up_proj",
|
| 40 |
+
"15.mlp.experts.down_proj",
|
| 41 |
+
"23.mlp.experts.gate_up_proj",
|
| 42 |
+
"23.mlp.experts.down_proj"
|
| 43 |
+
],
|
| 44 |
+
"task_type": null,
|
| 45 |
+
"trainable_token_indices": null,
|
| 46 |
+
"use_dora": false,
|
| 47 |
+
"use_qalora": false,
|
| 48 |
+
"use_rslora": false
|
| 49 |
+
}
|