Upload OlmoeForCausalLM
Browse files- config.json +33 -0
- generation_config.json +6 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "step23842-hf",
|
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 |
+
"rms_norm_eps": 1e-05,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 10000.0,
|
27 |
+
"router_aux_loss_coef": 0.01,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.48.1",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 50304
|
33 |
+
}
|
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": "4.48.1"
|
6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5a700fa91fd94e9d1a7ae523c5ae055f5879778a02ea19758edd37089da1ca
|
3 |
+
size 4993992240
|
model-00002-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f299f21e6de71f5334e937fd51a083bab8cffe55682488219e4082d9558fdba
|
3 |
+
size 4992966080
|
model-00003-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4491eb552fd917a6777260f75c88e714f3174fbba7dd69d44b97c4124ddcd56b
|
3 |
+
size 4992966080
|
model-00004-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aeea413752cd17a8e7c343aa436594a8158d279817e4993aa5df4b7c7cfdf22
|
3 |
+
size 4992966416
|
model-00005-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18c7f749af753359e10c33a9c5deec688b7155f7c01052937806cd351c52cc38
|
3 |
+
size 4992966680
|
model-00006-of-00006.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:299009ba118f5e918de33573a316ad3d3b9236651986fb1a14dc894f55269e67
|
3 |
+
size 2711184968
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|