Upload Pebble 25M model, config, and tokenizer artifacts
Browse files- config.json +22 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "pebble_25m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PebbleLM"
|
| 5 |
+
],
|
| 6 |
+
"vocab_size": 2048,
|
| 7 |
+
"d_model": 608,
|
| 8 |
+
"n_blocks": 8,
|
| 9 |
+
"n_heads": 8,
|
| 10 |
+
"att_hidden": 2432,
|
| 11 |
+
"rope_theta": 10000.0,
|
| 12 |
+
"seq_len": 2048,
|
| 13 |
+
"eos_token_id": 0,
|
| 14 |
+
"bos_token_id": 0,
|
| 15 |
+
"torch_dtype": "float32",
|
| 16 |
+
"mamba_d_state": 128,
|
| 17 |
+
"mamba_d_conv": 4,
|
| 18 |
+
"mamba_expand": 2,
|
| 19 |
+
"mamba_headdim": 64,
|
| 20 |
+
"block_pattern": "3:1 mamba:attn",
|
| 21 |
+
"transformers_version": "4.44.0"
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bf534a800165b6b79e1951a1cf743080f13268c81d0e58957b01d3a28188038
|
| 3 |
+
size 102933896
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3 |
+
"bos_token": "<|eos|>",
|
| 4 |
+
"eos_token": "<|eos|>",
|
| 5 |
+
"pad_token": null,
|
| 6 |
+
"unk_token": null,
|
| 7 |
+
"add_bos_token": false,
|
| 8 |
+
"add_eos_token": false,
|
| 9 |
+
"model_max_length": 2048,
|
| 10 |
+
"model_input_names": [
|
| 11 |
+
"input_ids"
|
| 12 |
+
],
|
| 13 |
+
"name_or_path": "pebble-bpe-2048",
|
| 14 |
+
"eos_token_id": 0,
|
| 15 |
+
"vocab_size": 2048
|
| 16 |
+
}
|