CJIS v3.0 cjis-copilot-full - Climate journalism multi-label classifier
Browse files- cjis_config.json +43 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
cjis_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model": "/content/drive/MyDrive/maai/mlm_climate_model",
|
| 3 |
+
"taxonomy_version": "v3.0",
|
| 4 |
+
"label_lists": {
|
| 5 |
+
"categories": [
|
| 6 |
+
"climate_governance_policy",
|
| 7 |
+
"climate_physical_impacts",
|
| 8 |
+
"climate_socio_environmental_impacts",
|
| 9 |
+
"energy_transition",
|
| 10 |
+
"climate_adaptation",
|
| 11 |
+
"economic_frameworks",
|
| 12 |
+
"climate_skepticism"
|
| 13 |
+
],
|
| 14 |
+
"themes": [
|
| 15 |
+
"emissions_carbon_pricing",
|
| 16 |
+
"climate_finance_development",
|
| 17 |
+
"food_security_public_health",
|
| 18 |
+
"renewable_energy_tech",
|
| 19 |
+
"fossil_fuel_industry",
|
| 20 |
+
"grid_infrastructure",
|
| 21 |
+
"just_transition",
|
| 22 |
+
"climate_litigation",
|
| 23 |
+
"extreme_weather_events",
|
| 24 |
+
"biodiversity_ecosystems"
|
| 25 |
+
],
|
| 26 |
+
"frames": [
|
| 27 |
+
"scientific",
|
| 28 |
+
"crisis",
|
| 29 |
+
"economic_solutions",
|
| 30 |
+
"political",
|
| 31 |
+
"justice_responsibility",
|
| 32 |
+
"health_ecological",
|
| 33 |
+
"security",
|
| 34 |
+
"human_interest"
|
| 35 |
+
],
|
| 36 |
+
"sentiments": [
|
| 37 |
+
"alarm_urgent",
|
| 38 |
+
"critical_skeptical",
|
| 39 |
+
"solution_oriented",
|
| 40 |
+
"neutral_balanced"
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e8843eff51b34c33dbc8b8e461ba881253b76da2c973d142a4ee04232d6c1f2
|
| 3 |
+
size 735504219
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"cls_token": "[CLS]",
|
| 7 |
+
"do_lower_case": false,
|
| 8 |
+
"eos_token": "[SEP]",
|
| 9 |
+
"is_local": true,
|
| 10 |
+
"mask_token": "[MASK]",
|
| 11 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 12 |
+
"model_specific_special_tokens": {},
|
| 13 |
+
"pad_token": "[PAD]",
|
| 14 |
+
"sep_token": "[SEP]",
|
| 15 |
+
"sp_model_kwargs": {},
|
| 16 |
+
"split_by_punct": false,
|
| 17 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 18 |
+
"unk_id": 3,
|
| 19 |
+
"unk_token": "[UNK]",
|
| 20 |
+
"vocab_type": "spm"
|
| 21 |
+
}
|