d4687d3207319b5b27feb4cfbca7639fabe0ceca4bfcab07df0705294e555dad
Browse files- config.json +4 -2
- generation_config.json +1 -1
- model.safetensors.index.json +0 -0
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",
|
@@ -26,14 +27,15 @@
|
|
26 |
"model_version": 1,
|
27 |
"outlier_channel_split": false,
|
28 |
"packsz": 4,
|
29 |
-
"rescale_WH": false
|
|
|
30 |
},
|
31 |
"rms_norm_eps": 1e-05,
|
32 |
"rope_scaling": null,
|
33 |
"rope_theta": 10000.0,
|
34 |
"tie_word_embeddings": false,
|
35 |
"torch_dtype": "float16",
|
36 |
-
"transformers_version": "4.
|
37 |
"use_cache": true,
|
38 |
"vocab_size": 32000
|
39 |
}
|
|
|
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",
|
|
|
27 |
"model_version": 1,
|
28 |
"outlier_channel_split": false,
|
29 |
"packsz": 4,
|
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
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
}
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|