whizzzzkid commited on
Commit
c7616c7
1 Parent(s): 8f62fdd

Upload StableLmForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +5 -3
  2. generation_config.json +2 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -4,8 +4,8 @@
4
  "StableLmForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 100257,
8
- "eos_token_id": 100257,
9
  "hidden_act": "silu",
10
  "hidden_dropout": 0.0,
11
  "hidden_size": 2048,
@@ -18,12 +18,14 @@
18
  "num_hidden_layers": 24,
19
  "num_key_value_heads": 32,
20
  "partial_rotary_factor": 0.25,
 
21
  "rope_scaling": null,
22
  "rope_theta": 10000,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.38.2",
26
- "use_cache": true,
 
27
  "use_qkv_bias": true,
28
  "vocab_size": 100352
29
  }
 
4
  "StableLmForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 100289,
8
+ "eos_token_id": 100290,
9
  "hidden_act": "silu",
10
  "hidden_dropout": 0.0,
11
  "hidden_size": 2048,
 
18
  "num_hidden_layers": 24,
19
  "num_key_value_heads": 32,
20
  "partial_rotary_factor": 0.25,
21
+ "qk_layernorm": false,
22
  "rope_scaling": null,
23
  "rope_theta": 10000,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.38.2",
27
+ "use_cache": false,
28
+ "use_parallel_residual": false,
29
  "use_qkv_bias": true,
30
  "vocab_size": 100352
31
  }
generation_config.json CHANGED
@@ -2,5 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 100289,
4
  "eos_token_id": 100290,
5
- "transformers_version": "4.38.2"
 
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 100289,
4
  "eos_token_id": 100290,
5
+ "transformers_version": "4.38.2",
6
+ "use_cache": false
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43fce82ce14e8f6f82c45c19df9370f946dbd92fb7910e8255235220c9f59e99
3
  size 3289069520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1025443ba622412cf045904147744eb18f457350d2ee676070235146ff166d1
3
  size 3289069520