Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +33 -0
- generation_config.json +4 -0
- generation_config_bak.json +6 -0
- metadata.json +1 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/OLMoE-1B-7B-0924",
|
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": 3072,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 2048,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "olmoe",
|
16 |
+
"norm_topk_prob": false,
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_experts": 32,
|
19 |
+
"num_experts_per_tok": 4,
|
20 |
+
"num_hidden_layers": 20,
|
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": "4.48.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 131072
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.48.2"
|
4 |
+
}
|
generation_config_bak.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": "4.48.2"
|
6 |
+
}
|
metadata.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"num_active_params": "3.07B", "total_params": "13.64B"}
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af5fed4ac32d36a9a0bded7307f7dd6187f4b54fe1eadd14479165a4c614cdbf
|
3 |
+
size 4983710256
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8c239c9e140d5cd364eb86c5a5c8bcbd323b213c25f5210c8f8bc0e05953c94
|
3 |
+
size 4983742760
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cde90abfe39dcaa6fa7f166c74a0f5a54624875bf2ffb1a5879fca6a3f69dba
|
3 |
+
size 4983742760
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ad8b3eb12d12ddfe10811dfc1ecb8f98519d0a1d3d439247acc567e4e0eea9
|
3 |
+
size 4983742760
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec3891cac2a84f03e0162c2fae14d28e016914f35a1bcef01211cd29495cd9f
|
3 |
+
size 4983742760
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0204bb0ea869cc898461832bc2bf5303bade8115a7139809a7799339e9ed3f35
|
3 |
+
size 4970741976
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebcb63845ecc5c87084c37d339a0b4758d5ef5d164fb6283332db77cb352aa8d
|
3 |
+
size 4996301192
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f5b2c215359e882b0be78fb22643793bf6d21786f032344d21f569a27db0949
|
3 |
+
size 4983742952
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:773ed0b384cf57988cd0ea12d9459a508dc08d6de6ae6a7613e9562f5f664bbd
|
3 |
+
size 4983742952
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88ef32d6ca88581bc72ec95ded1ea735e32cfd370e8245bc5c8f2a9421584476
|
3 |
+
size 4983742952
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68794ec2b29644751f9051f580ba3965da0823be3d1bd9a49d9a69894f7d44cf
|
3 |
+
size 4731670264
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
|
3 |
+
size 17078292
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|