Hugging Face's logo

hugging-science
/
E1-v2

Model card Files
xet
 Community
1
Bc-AI commited on
Commit
863821b
·
verified ·
1 Parent(s): f4cb317

Remove previous checkpoint folder

Browse files
Files changed (14) hide show
  1. adaptive-1b/checkpoints/step-000210763-451b3a2f/README.md +0 -4
  2. adaptive-1b/checkpoints/step-000210763-451b3a2f/config.json +0 -16
  3. adaptive-1b/checkpoints/step-000210763-451b3a2f/manifest.json +0 -38
  4. adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0000.safetensors +0 -3
  5. adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0001.safetensors +0 -3
  6. adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0002.safetensors +0 -3
  7. adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0003.safetensors +0 -3
  8. adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0000.pt +0 -3
  9. adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0001.pt +0 -3
  10. adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0002.pt +0 -3
  11. adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0003.pt +0 -3
  12. adaptive-1b/checkpoints/step-000210763-451b3a2f/tokenizer/tokenizer.json +0 -0
  13. adaptive-1b/checkpoints/step-000210763-451b3a2f/tokenizer/tokenizer_config.json +0 -17
  14. adaptive-1b/checkpoints/step-000210763-451b3a2f/training_state.pt +0 -3
adaptive-1b/checkpoints/step-000210763-451b3a2f/README.md DELETED
@@ -1,4 +0,0 @@
1
- # E1-v2 ADAPTIVE-1B training checkpoint
2
-
3
- Custom PyTorch MoE architecture, not Transformers AutoModel.
4
- Only load trusted optimizer/training pickle files.
 
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/config.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "model_name": "E1-v2",
3
- "implementation_version": 3,
4
- "d_model": 448,
5
- "n_layers": 16,
6
- "n_heads": 7,
7
- "n_kv_heads": 1,
8
- "expert_hidden": 192,
9
- "n_experts": 237,
10
- "max_k": 17,
11
- "skip_every": 3,
12
- "rope_theta": 10000.0,
13
- "sequence_length": 2048,
14
- "tokenizer_name": "mistralai/Mistral-7B-v0.3",
15
- "vocab_size": 32768
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/manifest.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "format_version": 3,
3
- "architecture": {
4
- "model_name": "E1-v2",
5
- "implementation_version": 3,
6
- "d_model": 448,
7
- "n_layers": 16,
8
- "n_heads": 7,
9
- "n_kv_heads": 1,
10
- "expert_hidden": 192,
11
- "n_experts": 237,
12
- "max_k": 17,
13
- "skip_every": 3,
14
- "rope_theta": 10000.0,
15
- "sequence_length": 2048,
16
- "tokenizer_name": "mistralai/Mistral-7B-v0.3",
17
- "vocab_size": 32768
18
- },
19
- "progress": {
20
- "step": 210763,
21
- "tokens": 13812563968,
22
- "sessions": 5,
23
- "skipped_updates": 0,
24
- "consecutive_skips": 0
25
- },
26
- "model_shards": [
27
- "model-0000.safetensors",
28
- "model-0001.safetensors",
29
- "model-0002.safetensors",
30
- "model-0003.safetensors"
31
- ],
32
- "optimizer_shards": [
33
- "optimizer-0000.pt",
34
- "optimizer-0001.pt",
35
- "optimizer-0002.pt",
36
- "optimizer-0003.pt"
37
- ]
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0000.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:01eff44bc0d37ff93711d93c061b087cb8e79a2a27fdc295737c5e793ef359e0
3
- size 524277178
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0001.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d6084f268371cfac7693fac65dcae1c8a34cac6b15c8fe0af3be8dce1f78638
3
- size 493785560
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aca124d2c76b88d390b5c82306c85a79d5c6cc8b5040c9a92f74bb72235ec01
3
- size 493785552
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/model-0003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0865ed202b0438e3187356426e29ff23353a5ae74beb24cf3d214c271805110b
3
- size 492654158
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0000.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:798c3fac59917a81f2999d219a9be4df4cd394b8ae758a7c73b2d97abbd53080
3
- size 532612169
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0001.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb8b2394669d210f4b75ed4555d54c1b48797af67c3f607e74e17365a37dbb52
3
- size 501618497
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0002.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:57aa114e3c6d9ee0895cc0f712aa3e3bdcc1dacd3c41058257e7f53a0941a2aa
3
- size 501618561
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/optimizer-0003.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:69f77cca0b1d5b918ce4cb0b770c61495c319812b4e7981012988241d04022cc
3
- size 500447511
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/tokenizer/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/tokenizer/tokenizer_config.json DELETED
@@ -1,17 +0,0 @@
1
- {
2
- "add_prefix_space": true,
3
- "backend": "tokenizers",
4
- "bos_token": "<s>",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "</s>",
7
- "is_local": true,
8
- "legacy": false,
9
- "local_files_only": false,
10
- "model_max_length": 1000000000000,
11
- "pad_token": null,
12
- "sp_model_kwargs": {},
13
- "spaces_between_special_tokens": false,
14
- "tokenizer_class": "TokenizersBackend",
15
- "unk_token": "<unk>",
16
- "use_default_system_prompt": false
17
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
adaptive-1b/checkpoints/step-000210763-451b3a2f/training_state.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2ae57db69622aaaad6dc84a0b3eaaf1bfd4356a2cd2144db407168b60f78ce2
3
- size 24349