Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +39 -0
- generation_config.json +4 -0
- model.safetensors +3 -0
- special_tokens_map.json +34 -0
- tokenizer_config.json +60 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 100279,
|
3 |
+
"<|im_start|>": 100278,
|
4 |
+
"<|pad|>": 100277
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "databricks/dbrx-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"DbrxForCausalLM"
|
5 |
+
],
|
6 |
+
"attn_config": {
|
7 |
+
"clip_qkv": 8,
|
8 |
+
"kv_n_heads": 2,
|
9 |
+
"model_type": "",
|
10 |
+
"rope_theta": 500000
|
11 |
+
},
|
12 |
+
"auto_map": {
|
13 |
+
"AutoConfig": "databricks/dbrx-instruct--configuration_dbrx.DbrxConfig",
|
14 |
+
"AutoModelForCausalLM": "databricks/dbrx-instruct--modeling_dbrx.DbrxForCausalLM"
|
15 |
+
},
|
16 |
+
"d_model": 4,
|
17 |
+
"emb_pdrop": 0.0,
|
18 |
+
"ffn_config": {
|
19 |
+
"ffn_hidden_size": 8,
|
20 |
+
"model_type": "",
|
21 |
+
"moe_jitter_eps": 0,
|
22 |
+
"moe_loss_weight": 0.05,
|
23 |
+
"moe_num_experts": 16,
|
24 |
+
"moe_top_k": 4
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"max_seq_len": 32768,
|
28 |
+
"model_type": "dbrx",
|
29 |
+
"n_heads": 4,
|
30 |
+
"n_layers": 2,
|
31 |
+
"output_router_logits": false,
|
32 |
+
"resid_pdrop": 0.0,
|
33 |
+
"router_aux_loss_coef": 0.05,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float16",
|
36 |
+
"transformers_version": "4.38.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 100352
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.38.1"
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32ef66769d8089a9518c9e53ee8b350c81f31b7d4d0e505fe58bd34a5daa3c9
|
3 |
+
size 1614328
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|pad|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"100257": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"100277": {
|
15 |
+
"content": "<|pad|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"100278": {
|
23 |
+
"content": "<|im_start|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"100279": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"additional_special_tokens": [
|
40 |
+
"<|im_start|>",
|
41 |
+
"<|im_end|>"
|
42 |
+
],
|
43 |
+
"auto_map": {
|
44 |
+
"AutoTokenizer": [
|
45 |
+
"databricks/dbrx-instruct--tiktoken.TiktokenTokenizerWrapper",
|
46 |
+
null
|
47 |
+
]
|
48 |
+
},
|
49 |
+
"bos_token": "<|endoftext|>",
|
50 |
+
"clean_up_tokenization_spaces": true,
|
51 |
+
"encoding_name": null,
|
52 |
+
"eos_token": "<|endoftext|>",
|
53 |
+
"errors": "replace",
|
54 |
+
"model_max_length": 1000000000000000019884624838656,
|
55 |
+
"model_name": "gpt-4",
|
56 |
+
"pad_token": "<|pad|>",
|
57 |
+
"tokenizer_class": "TiktokenTokenizerWrapper",
|
58 |
+
"unk_token": "<|endoftext|>",
|
59 |
+
"use_default_system_prompt": true
|
60 |
+
}
|