francislabounty commited on
Commit
eea4fdd
1 Parent(s): 5fff4a4

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "serpdotai/sparsetral-16x7B-v2",
3
+ "adapter_dim": 512,
4
+ "adapter_dropout": 0.0,
5
+ "architectures": [
6
+ "MistralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "serpdotai/sparsetral-16x7B-v2--configuration_sparsetral.SparsetralConfig",
11
+ "AutoModel": "serpdotai/sparsetral-16x7B-v2--modeling_sparsetral.MistralModel",
12
+ "AutoModelForCausalLM": "serpdotai/sparsetral-16x7B-v2--modeling_sparsetral.MistralForCausalLM"
13
+ },
14
+ "bos_token_id": 1,
15
+ "eos_token_id": 2,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 4096,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 14336,
20
+ "max_position_embeddings": 32768,
21
+ "model_type": "mistral",
22
+ "moe_dtype": "bfloat16",
23
+ "moe_scaling": 1,
24
+ "num_attention_heads": 32,
25
+ "num_experts": 16,
26
+ "num_hidden_layers": 32,
27
+ "num_key_value_heads": 8,
28
+ "output_router_logits": false,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_theta": 1000000.0,
32
+ "router_aux_loss_coef": 0.01,
33
+ "sliding_window": null,
34
+ "tie_word_embeddings": false,
35
+ "topk": 4,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.37.2",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.2"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aad4d4e6a586ddc156d97b6bb38fecf64277234ed60a84636ffbd1f9dc29058
3
+ size 4910657472
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012b1b87bf70259293d0724e042a5ec80f3180e7364f3432a89c998a18087418
3
+ size 4996774472
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d00157bcab770b982b61e65fd0a1589d9f2f7aaf8820ccdf8f4896985fb907
3
+ size 4937939192
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e0893636acf17ad0d95dc0480a7e94858239e774b5c5b456ab3a4368124a7d
3
+ size 3937433264
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }