Upload folder using huggingface_hub
Browse files- config.json +35 -30
- special_tokens_map.json +5 -0
- tokenizer_config.json +9 -0
config.json
CHANGED
@@ -1,31 +1,36 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
"
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "MBZUAI-LLM/SlimPajama-DC",
|
3 |
+
"activation_function": "swiglu",
|
4 |
+
"architectures": [
|
5 |
+
"BTLMLMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "configuration_btlm.BTLMConfig",
|
10 |
+
"AutoModel": "MBZUAI-LLM/SlimPajama-DC--modeling_btlm.BTLMModel",
|
11 |
+
"AutoModelForCausalLM": "MBZUAI-LLM/SlimPajama-DC--modeling_btlm.BTLMLMHeadModel"
|
12 |
+
},
|
13 |
+
"bos_token_id": 50256,
|
14 |
+
"embd_pdrop": 0.0,
|
15 |
+
"embeddings_scale": 14.6,
|
16 |
+
"eos_token_id": 0,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"layer_norm_epsilon": 1e-05,
|
19 |
+
"model_type": "btlm",
|
20 |
+
"n_embd": 2048,
|
21 |
+
"n_head": 16,
|
22 |
+
"n_inner": 5461,
|
23 |
+
"n_layer": 24,
|
24 |
+
"n_positions": 2048,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"position_embedding_type": "alibi",
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.0,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"scale_qk_dot_by_d": true,
|
32 |
+
"transformers_version": "4.32.1",
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 50277,
|
35 |
+
"width_scale": 0.2775
|
36 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 8192,
|
7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|