sharpenb commited on
Commit
e611733
1 Parent(s): c77e6f6

46b466877d14fb2c7f90ec28aea889c1dcffdd6f6fdf53c10a4af001af6404cd

Browse files
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "SinclairSchneider/dbrx-instruct-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-instruct-quantization-fixed--configuration_dbrx.DbrxConfig",
14
+ "AutoModelForCausalLM": "SinclairSchneider/dbrx-instruct-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,
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 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 100257,
5
+ 100279
6
+ ],
7
+ "transformers_version": "4.39.2"
8
+ }
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c09710cf02b44be76007e8ddc836d335f3e5f008bf247431d55c4afbc0a3b17
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "SinclairSchneider/dbrx-instruct-quantization-fixed--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
+ }