Upload trained SFT model
Browse files- README.md +8 -0
- reference/adapter_config.json +7 -4
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,6 +1,13 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-14B
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
@@ -199,4 +206,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 199 |
[More Information Needed]
|
| 200 |
### Framework versions
|
| 201 |
|
|
|
|
| 202 |
- PEFT 0.15.2
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-14B
|
| 3 |
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- base_model:adapter:Qwen/Qwen3-14B
|
| 6 |
+
- lora
|
| 7 |
+
- sft
|
| 8 |
+
- transformers
|
| 9 |
+
- trl
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
---
|
| 12 |
|
| 13 |
# Model Card for Model ID
|
|
|
|
| 206 |
[More Information Needed]
|
| 207 |
### Framework versions
|
| 208 |
|
| 209 |
+
- PEFT 0.17.0
|
| 210 |
- PEFT 0.15.2
|
reference/adapter_config.json
CHANGED
|
@@ -20,20 +20,23 @@
|
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
|
|
|
| 23 |
"r": 16,
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"k_proj",
|
| 28 |
-
"q_proj",
|
| 29 |
"v_proj",
|
| 30 |
"gate_proj",
|
| 31 |
-
"
|
|
|
|
| 32 |
"down_proj",
|
| 33 |
-
"
|
|
|
|
| 34 |
],
|
|
|
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
| 37 |
"use_dora": false,
|
|
|
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
|
|
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
| 23 |
+
"qalora_group_size": 16,
|
| 24 |
"r": 16,
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
| 28 |
"v_proj",
|
| 29 |
"gate_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
"down_proj",
|
| 33 |
+
"q_proj",
|
| 34 |
+
"o_proj"
|
| 35 |
],
|
| 36 |
+
"target_parameters": null,
|
| 37 |
"task_type": "CAUSAL_LM",
|
| 38 |
"trainable_token_indices": null,
|
| 39 |
"use_dora": false,
|
| 40 |
+
"use_qalora": false,
|
| 41 |
"use_rslora": false
|
| 42 |
}
|
training_args.bin
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:e7f9f59b7f7516a9e541c7b5a2f940bf819577012b69232236305f64d3370c38
|
| 3 |
+
size 6289
|