Upload model
Browse files- README.md +2 -0
- config.json +3 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
- maths
|
| 7 |
- gpt2
|
| 8 |
- mathgpt2
|
|
|
|
|
|
|
| 9 |
datasets:
|
| 10 |
- meta-math/MetaMathQA
|
| 11 |
- ArtifactAI/arxiv-math-instruct-50k
|
|
|
|
| 6 |
- maths
|
| 7 |
- gpt2
|
| 8 |
- mathgpt2
|
| 9 |
+
- trl
|
| 10 |
+
- sft
|
| 11 |
datasets:
|
| 12 |
- meta-math/MetaMathQA
|
| 13 |
- ArtifactAI/arxiv-math-instruct-50k
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Sharathhebbar24/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -32,8 +32,8 @@
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
-
"torch_dtype": "
|
| 36 |
-
"transformers_version": "4.
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 50257
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Sharathhebbar24/math_gpt2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 32 |
"max_length": 50
|
| 33 |
}
|
| 34 |
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.39.3",
|
| 37 |
"use_cache": true,
|
| 38 |
"vocab_size": 50257
|
| 39 |
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 50256,
|
| 4 |
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.39.3"
|
| 6 |
}
|
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 sha256:76e4cb5e488f9e194cf936ccea0fa8fdbb2fc45f19a6bf7d05526f744c96146a
|
| 3 |
+
size 497774208
|