Add lightweight ModernBERT-base 164M model variant in BF16 (~312MB)
Browse filesAdds subfolder base-164m containing model.safetensors (312MB BF16), rl_agent_config.json, and tokenizer files.
base-164m/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e240a85c95a85a0089c220c2630225978e4af275676b2cd8c21e22479586df66
|
| 3 |
+
size 327984908
|
base-164m/rl_agent_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"encoder": "answerdotai/ModernBERT-base",
|
| 3 |
+
"head_layers": 2,
|
| 4 |
+
"max_len": 1024,
|
| 5 |
+
"head_max_len": 256,
|
| 6 |
+
"max_prefixes": 6,
|
| 7 |
+
"act_costs": {
|
| 8 |
+
"escalate": 0.5
|
| 9 |
+
},
|
| 10 |
+
"cost_wrong_act": 3.0,
|
| 11 |
+
"amp_dtype": "bf16",
|
| 12 |
+
"model_name": "code-oracle-laya-modernbert-base",
|
| 13 |
+
"temperature": [
|
| 14 |
+
1.0,
|
| 15 |
+
1.0,
|
| 16 |
+
1.0
|
| 17 |
+
],
|
| 18 |
+
"temperature_by_options": {
|
| 19 |
+
"choice:2": 1.9,
|
| 20 |
+
"score:3-5": 1.25
|
| 21 |
+
},
|
| 22 |
+
"dataset_samples": 2400,
|
| 23 |
+
"accuracy": 0.995
|
| 24 |
+
}
|
base-164m/tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
base-164m/tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"local_files_only": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_input_names": [
|
| 7 |
+
"input_ids",
|
| 8 |
+
"attention_mask"
|
| 9 |
+
],
|
| 10 |
+
"model_max_length": 8192,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"sep_token": "[SEP]",
|
| 13 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|