End of training
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
-
license:
|
| 4 |
-
base_model: deepseek-ai/
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# Baha_DeepSeek
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [deepseek-ai/
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: deepseek-ai/deepseek-llm-7b-chat
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
|
|
|
| 14 |
|
| 15 |
# Baha_DeepSeek
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-chat](https://huggingface.co/deepseek-ai/deepseek-llm-7b-chat) on the None dataset.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
adapter_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "deepseek-ai/
|
| 5 |
"bias": "none",
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
| 26 |
"q_proj",
|
| 27 |
-
"gate_proj",
|
| 28 |
"k_proj",
|
| 29 |
"up_proj",
|
|
|
|
| 30 |
"v_proj",
|
| 31 |
-
"o_proj"
|
| 32 |
-
"down_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-chat",
|
| 5 |
"bias": "none",
|
| 6 |
"eva_config": null,
|
| 7 |
"exclude_modules": null,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"down_proj",
|
| 27 |
"q_proj",
|
|
|
|
| 28 |
"k_proj",
|
| 29 |
"up_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
"v_proj",
|
| 32 |
+
"o_proj"
|
|
|
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
adapter_model.safetensors
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 sha256:92e73d4da0d2c21dec69bb1f212744ddd671b7871e66badc9232a2666817a1a1
|
| 3 |
+
size 75012288
|
runs/Jan30_11-29-35_78c1692bcb61/events.out.tfevents.1738236577.78c1692bcb61.712.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca85a5590d891f87878def1e96ed2c0c75d2f7445afb2a160efd3da25a92aaa0
|
| 3 |
+
size 5513
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7010401aca29a1002512b9a637119571f9fdf936ef2033f41a5f62e062a41ccc
|
| 3 |
size 5368
|