10b851337b4f1c99f82c53e866003b58b0ff5c82d443ed19932bf04437b1b297
Browse files- config.json +3 -2
- generation_config.json +1 -1
config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
|
|
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"hidden_act": "silu",
|
|
@@ -27,14 +28,14 @@
|
|
| 27 |
"outlier_channel_split": false,
|
| 28 |
"packsz": 2,
|
| 29 |
"rescale_WH": false,
|
| 30 |
-
"resid_scale_override":
|
| 31 |
},
|
| 32 |
"rms_norm_eps": 1e-05,
|
| 33 |
"rope_scaling": null,
|
| 34 |
"rope_theta": 10000.0,
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
"torch_dtype": "float16",
|
| 37 |
-
"transformers_version": "4.
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 32000
|
| 40 |
}
|
|
|
|
| 4 |
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
"bos_token_id": 1,
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"hidden_act": "silu",
|
|
|
|
| 28 |
"outlier_channel_split": false,
|
| 29 |
"packsz": 2,
|
| 30 |
"rescale_WH": false,
|
| 31 |
+
"resid_scale_override": -1
|
| 32 |
},
|
| 33 |
"rms_norm_eps": 1e-05,
|
| 34 |
"rope_scaling": null,
|
| 35 |
"rope_theta": 10000.0,
|
| 36 |
"tie_word_embeddings": false,
|
| 37 |
"torch_dtype": "float16",
|
| 38 |
+
"transformers_version": "4.36.2",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 32000
|
| 41 |
}
|
generation_config.json
CHANGED
|
@@ -6,5 +6,5 @@
|
|
| 6 |
"pad_token_id": 0,
|
| 7 |
"temperature": 0.6,
|
| 8 |
"top_p": 0.9,
|
| 9 |
-
"transformers_version": "4.
|
| 10 |
}
|
|
|
|
| 6 |
"pad_token_id": 0,
|
| 7 |
"temperature": 0.6,
|
| 8 |
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.36.2"
|
| 10 |
}
|