Upload Novi Mini Base checkpoint 321000
Browse files- config.json +26 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture_style": "bananamind2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ProjectKairoMiniForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"intermediate_size": 768,
|
| 12 |
+
"lft": false,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "bananaall",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 10,
|
| 17 |
+
"num_key_value_heads": 2,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 100000.0,
|
| 21 |
+
"ternary": false,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"transformers_version": "5.14.1",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 8192
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
2
|
| 6 |
+
],
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "5.14.1",
|
| 11 |
+
"use_cache": false
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2557771fef678bb48624b13d96ce0aa4f4488fe6d66f6a71cfa064ef295ecfd2
|
| 3 |
+
size 48271912
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:831efe0c39bf037b02ef3a5b302bcd551bd696fb02db4dc5fae000731eefca2f
|
| 3 |
+
size 96619275
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c606353130c2f569a7dc85ef398b983c82fe6cc91d7815836f4736a6097ce89
|
| 3 |
+
size 14709
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aae7e11eaf551f2a9653e4bcc825b300500b2d11fb63d11fb8b5960c294e8538
|
| 3 |
+
size 1465
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "[BOS]",
|
| 4 |
+
"eos_token": "[EOS]",
|
| 5 |
+
"is_local": true,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"model_max_length": 2048,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"tokenizer_class": "TokenizersBackend",
|
| 10 |
+
"unk_token": "[UNK]"
|
| 11 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb8320d13411f616e883016b708e23b7b2170a2d78e7baecd5776c2a4501c2ff
|
| 3 |
+
size 5201
|