Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- adapter_config.json +5 -1
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "unsloth/gemma-3n-
|
| 5 |
"bias": "none",
|
|
|
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
| 8 |
"fan_in_fan_out": false,
|
|
@@ -19,11 +20,14 @@
|
|
| 19 |
"megatron_core": "megatron.core",
|
| 20 |
"modules_to_save": null,
|
| 21 |
"peft_type": "LORA",
|
|
|
|
| 22 |
"r": 8,
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"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)))",
|
| 26 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 27 |
"use_dora": false,
|
|
|
|
| 28 |
"use_rslora": false
|
| 29 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/gemma-3n-E4B-it",
|
| 5 |
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
|
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
"r": 8,
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"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)))",
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
+
"trainable_token_indices": null,
|
| 30 |
"use_dora": false,
|
| 31 |
+
"use_qalora": false,
|
| 32 |
"use_rslora": false
|
| 33 |
}
|
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 sha256:3d8f91acb7d604ededf23a5a932f0353af8a416a2b8bd43dbc82d39825d00d2a
|
| 3 |
size 76913008
|