at676 commited on
Commit
4f6cb44
1 Parent(s): d0157ef

Upload folder using huggingface_hub (#4)

Browse files

- 5b935628bc2d94ea952ace903929d1a9a3f92f7ee8790fc35af61f27d6fb77d9 (24896d257878fb4cb1e1ef20257cb1964007b424)
- 7f592f5e72da2956591c42252259999f70f6a8cd03ab47a7ebdb5908538ea2b3 (b29eca999191f624b523a19f175aa68f37ef5326)
- 10635252fb85e1f5cc25b0281f0235b52ea6d0acecae3d258e9458f8beee7663 (09c21bdb4d7cab9cb414f31cc52cce3ed3d176d6)
- 0dd7112ff1723da48c310c7764dcf955eedf9246c3ec75932006e4584d35f8db (ae03d0a8cebc6e697381d9566fec2c59604284dc)
- 456085e0dd131097fdf8c41862de0c934f914dc81631b017e1ce42c67f5a64d6 (66485936db287345ca685f9d27ac951c36f766e0)

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": "4.34.0",
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-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": "4.34.0"
10
  }
 
6
  "pad_token_id": 0,
7
  "temperature": 0.6,
8
  "top_p": 0.9,
9
+ "transformers_version": "4.36.2"
10
  }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614ed7f1a5c12d21f2d8149e2738e4bb26d6f2410ede66dd84138fdf57ac40ee
3
+ size 4964068056
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b523cabe0f6eebc29885c2a594f7da8ef59e7839c4c7ee04efff781e585039b
3
+ size 4985874080
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5081b94724d83118bfeaeed307280ed31acf405091e4a67c78be1df3b7147d
3
+ size 4964866176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31efb0f29baadadb0057e7158e3d7ce64d53f429742824be3f89767d3e8a9b88
3
+ size 3271337328
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff