Safetensors
English
olmoe
Mixture of Experts
olmo
jacobmorrison commited on
Commit
7d49262
1 Parent(s): 93cf67e

Upload OlmoeForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "olmoe-sft/",
3
+ "architectures": [
4
+ "OlmoeForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": null,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1024,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "olmoe",
16
+ "norm_topk_prob": false,
17
+ "num_attention_heads": 16,
18
+ "num_experts": 64,
19
+ "num_experts_per_tok": 8,
20
+ "num_hidden_layers": 16,
21
+ "num_key_value_heads": 16,
22
+ "output_router_logits": false,
23
+ "pad_token_id": 1,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "router_aux_loss_coef": 0.001,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.44.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 50304
32
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.44.0.dev0"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb91fc3570bc49c613773ec760eca6a17c7e0b8caba371882b820b66b1df49b
3
+ size 4997744872
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67b73b712ea70ff68799c2ab20c1282c8abb829cfb34d97645c30e729fdbafe
3
+ size 4997235176
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd30f88d43bfc1e5d42b042543d552d98a1125bfbd0064be0c50cef097607da2
3
+ size 3843741912
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff