at676 commited on
Commit
c77fe43
1 Parent(s): 42807d6

Upload folder using huggingface_hub (#4)

Browse files

- fc624eac4cb17fd4499964005dcf8e2047a36816ea90ea8673418565e5831c49 (c539a836adaa65709b1e2f395760bfbcb58aa931)
- 65c6d26b94a6964e8b6e8f228ac579b4779b0bd318bb08bcf183ce2004b2281d (019643e67785e2b9fc4aff4eca8a1aa664c0d361)
- 1929e65e58111eb5afe23a88d97e4faf1fd8207eac5982811f3733d308aed225 (81a9af41f72690374e55e0e004a05933274f7935)

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-06,
32
  "rope_scaling": null,
33
  "rope_theta": 10000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "float16",
36
- "transformers_version": "4.34.0",
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-06,
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": "4.34.0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
  }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cec7a95f97475a87aa11e8755c4410b27ad7bc77d82021ee9f8b91656b5fcf1
3
+ size 4982062964
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad6139519db4e207fe5ad90a8ee4b5e3c3596974c0b0cd29303114ef9fdedf91
3
+ size 3910057956
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff