Upload folder using huggingface_hub
#1
by
sharpenb
- opened
- config.json +56 -0
- generation_config.json +7 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +31 -0
config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SinclairSchneider/dbrx-base-quantization-fixed",
|
3 |
+
"architectures": [
|
4 |
+
"DbrxForCausalLM"
|
5 |
+
],
|
6 |
+
"attn_config": {
|
7 |
+
"clip_qkv": 8,
|
8 |
+
"kv_n_heads": 8,
|
9 |
+
"model_type": "",
|
10 |
+
"rope_theta": 500000
|
11 |
+
},
|
12 |
+
"auto_map": {
|
13 |
+
"AutoConfig": "SinclairSchneider/dbrx-base-quantization-fixed--configuration_dbrx.DbrxConfig",
|
14 |
+
"AutoModelForCausalLM": "SinclairSchneider/dbrx-base-quantization-fixed--modeling_dbrx.DbrxForCausalLM"
|
15 |
+
},
|
16 |
+
"d_model": 6144,
|
17 |
+
"emb_pdrop": 0.0,
|
18 |
+
"ffn_config": {
|
19 |
+
"ffn_hidden_size": 10752,
|
20 |
+
"model_type": "",
|
21 |
+
"moe_jitter_eps": 0.01,
|
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": 48,
|
30 |
+
"n_layers": 40,
|
31 |
+
"output_router_logits": false,
|
32 |
+
"quantization_config": {
|
33 |
+
"_load_in_4bit": true,
|
34 |
+
"_load_in_8bit": false,
|
35 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
36 |
+
"bnb_4bit_quant_storage": "uint8",
|
37 |
+
"bnb_4bit_quant_type": "fp4",
|
38 |
+
"bnb_4bit_use_double_quant": true,
|
39 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
40 |
+
"llm_int8_has_fp16_weight": false,
|
41 |
+
"llm_int8_skip_modules": [
|
42 |
+
"lm_head"
|
43 |
+
],
|
44 |
+
"llm_int8_threshold": 6.0,
|
45 |
+
"load_in_4bit": true,
|
46 |
+
"load_in_8bit": false,
|
47 |
+
"quant_method": "bitsandbytes"
|
48 |
+
},
|
49 |
+
"resid_pdrop": 0.0,
|
50 |
+
"router_aux_loss_coef": 0.05,
|
51 |
+
"tie_word_embeddings": false,
|
52 |
+
"torch_dtype": "bfloat16",
|
53 |
+
"transformers_version": "4.39.2",
|
54 |
+
"use_cache": true,
|
55 |
+
"vocab_size": 100352
|
56 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": [
|
4 |
+
100257
|
5 |
+
],
|
6 |
+
"transformers_version": "4.39.2"
|
7 |
+
}
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae289985668b566607652fdee6bf9a3a28249888b9f684977d05b9bb829f0090
|
3 |
+
size 4982218709
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db4af6fde7f1f819f6ca0b98eb96953f8b835355ed54fcde17cc7ca6377d13f
|
3 |
+
size 4975991632
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7f8113efc1df3e11a1c073e19a7fecf15baeaef4d6176aa5fe778fab2059d53
|
3 |
+
size 4975991624
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d81fa410dd0a404a4984473eee172defaff2830928a609e120bdedd50f65e8b0
|
3 |
+
size 4975991970
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bbc860da4a5e4e9ba882ff2cf5b357814eb82e16b707c6801a90af6c6dc6855
|
3 |
+
size 4975992530
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9b7af2464a3a1b03073217f9737da50e01eb7643b268976864941a80951e6b6
|
3 |
+
size 4975992543
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f497407ea4c8026de9bf78e889adaa6540b666ac817f79126e11a98b74a7c0ac
|
3 |
+
size 4998646312
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8192f7535e089bceb3ec16edf09bca830084cfe5ceb95619daec96b8c606c800
|
3 |
+
size 4975980115
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f6228c02c861e0912a1e8965d299512155d0b75681ef784df2b28104004e77d
|
3 |
+
size 4975992524
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ae4681f2ac089a939afa8071f1217d81f5cb62e55d8d3652b1986d367636e4
|
3 |
+
size 4975992525
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ea8a809163d7f33bccce674e430ebd707e8e3c27d53f24a414beef6a8d5339d
|
3 |
+
size 4975992509
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed88bd9b52378086413a7307619980875b8d34069a684c5e746a7f44c036ea6b
|
3 |
+
size 4975992518
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:160eee7393384b95effa6cebf12f2d6150e7c096c9037d0391128c074d5689d1
|
3 |
+
size 4975992539
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fabb40d134aac45539a87224890fc3d1814a9d1afd7c8a556c388525c304d008
|
3 |
+
size 3771747556
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4137a4f0a61bdd5e1c30fcfd06aa7478e8de2362d0f66b4b26f37cf8c6560df
|
3 |
+
size 1233125504
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"100257": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
}
|
13 |
+
},
|
14 |
+
"auto_map": {
|
15 |
+
"AutoTokenizer": [
|
16 |
+
"SinclairSchneider/dbrx-base-quantization-fixed--tiktoken.TiktokenTokenizerWrapper",
|
17 |
+
null
|
18 |
+
]
|
19 |
+
},
|
20 |
+
"bos_token": "<|endoftext|>",
|
21 |
+
"clean_up_tokenization_spaces": true,
|
22 |
+
"encoding_name": null,
|
23 |
+
"eos_token": "<|endoftext|>",
|
24 |
+
"errors": "replace",
|
25 |
+
"model_max_length": 1000000000000000019884624838656,
|
26 |
+
"model_name": "gpt-4",
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"tokenizer_class": "TiktokenTokenizerWrapper",
|
29 |
+
"unk_token": "<|endoftext|>",
|
30 |
+
"use_default_system_prompt": true
|
31 |
+
}
|