Training in progress, step 50
Browse files- config.json +1 -2
- model.safetensors +1 -1
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
@@ -22,7 +21,7 @@
|
|
| 22 |
"sliding_window": 4096,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": false,
|
| 27 |
"use_mrope": false,
|
| 28 |
"use_sliding_window": false,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2ForCausalLM"
|
| 4 |
],
|
|
|
|
| 21 |
"sliding_window": 4096,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.51.3",
|
| 25 |
"use_cache": false,
|
| 26 |
"use_mrope": false,
|
| 27 |
"use_sliding_window": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3554214752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dd52af96fb70f61474fec62c642622f57cb36ab2ec272c811f2d6cf156666a0
|
| 3 |
size 3554214752
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a175c7d983a323db3f7998a7f8b61dd29da4ee9902480e357e93a1ec693abf33
|
| 3 |
size 8184
|