Sugyeong commited on
Commit
c278ec6
1 Parent(s): ff85390

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
3
+ "adapter_dim": 64,
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_camelidae.CamelidaeConfig",
9
+ "AutoModelForCausalLM": "modeling_camelidae.LlamaForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "max_position_embeddings": 4096,
18
+ "model_type": "llama",
19
+ "moe_dtype": "bfloat16",
20
+ "moe_scaling": 0.25,
21
+ "num_attention_heads": 32,
22
+ "num_clusters": 4,
23
+ "num_experts": 8,
24
+ "num_hidden_layers": 32,
25
+ "num_key_value_heads": 32,
26
+ "output_router_logits": false,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": null,
30
+ "tie_word_embeddings": false,
31
+ "topk": 2,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.34.0.dev0",
34
+ "use_cache": true,
35
+ "vocab_size": 32000
36
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.0.dev0"
10
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9459a37c109f2000b38eefc12edda703fb3aca0f50efd14848a08f8a9fced685
3
+ size 9978720339
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4675b272a23bf1da707519206ef4da4b08d466d7ef9d8d2eabbe9f62c323b65e
3
+ size 4581158713
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff