Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +3 -0
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -24,12 +24,15 @@
|
|
| 24 |
"megatron_core": "megatron.core",
|
| 25 |
"modules_to_save": null,
|
| 26 |
"peft_type": "LORA",
|
|
|
|
| 27 |
"r": 8,
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection)))",
|
|
|
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"trainable_token_indices": null,
|
| 33 |
"use_dora": false,
|
|
|
|
| 34 |
"use_rslora": false
|
| 35 |
}
|
|
|
|
| 24 |
"megatron_core": "megatron.core",
|
| 25 |
"modules_to_save": null,
|
| 26 |
"peft_type": "LORA",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
"r": 8,
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection)))",
|
| 32 |
+
"target_parameters": null,
|
| 33 |
"task_type": "CAUSAL_LM",
|
| 34 |
"trainable_token_indices": null,
|
| 35 |
"use_dora": false,
|
| 36 |
+
"use_qalora": false,
|
| 37 |
"use_rslora": false
|
| 38 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 76913008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f703012a6e9722a8f7daad2bd6dc6fecdc4ee5af3da0b6032b478ffa66d63b0
|
| 3 |
size 76913008
|