Upload BharataiForCausalLM
Browse files- config.json +6 -1
- model.py +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,8 +1,12 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"attention_bias": false,
|
| 3 |
"attention_dropout": 0.0,
|
| 4 |
"auto_map": {
|
| 5 |
-
"AutoConfig": "config.BharataiConfig"
|
|
|
|
| 6 |
},
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
|
@@ -20,6 +24,7 @@
|
|
| 20 |
"rope_scaling": null,
|
| 21 |
"rope_theta": 10000.0,
|
| 22 |
"tie_word_embeddings": false,
|
|
|
|
| 23 |
"transformers_version": "4.36.0.dev0",
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 5000
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BharataiForCausalLM"
|
| 4 |
+
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"auto_map": {
|
| 8 |
+
"AutoConfig": "config.BharataiConfig",
|
| 9 |
+
"AutoModelForCausalLM": "model.BharataiForCausalLM"
|
| 10 |
},
|
| 11 |
"bos_token_id": 1,
|
| 12 |
"eos_token_id": 2,
|
|
|
|
| 24 |
"rope_scaling": null,
|
| 25 |
"rope_theta": 10000.0,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
"transformers_version": "4.36.0.dev0",
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 5000
|
model.py
CHANGED
|
@@ -1218,4 +1218,4 @@ class BharataiForSequenceClassification(BharataiPreTrainedModel):
|
|
| 1218 |
past_key_values=transformer_outputs.past_key_values,
|
| 1219 |
hidden_states=transformer_outputs.hidden_states,
|
| 1220 |
attentions=transformer_outputs.attentions,
|
| 1221 |
-
)
|
|
|
|
| 1218 |
past_key_values=transformer_outputs.past_key_values,
|
| 1219 |
hidden_states=transformer_outputs.hidden_states,
|
| 1220 |
attentions=transformer_outputs.attentions,
|
| 1221 |
+
)
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 595142768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d979701fe48484e0a277a01296f98140cd6e786359d9b1d5273ba24a1377f8af
|
| 3 |
size 595142768
|