gabrielmbmb HF staff commited on
Commit
889104d
1 Parent(s): 601b42b

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gabrielmbmb/Upcycled-Qwen1.5-MoE2.7B",
3
+ "architectures": [
4
+ "Qwen2MoeForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 21,
16
+ "model_type": "qwen2_moe",
17
+ "moe_intermediate_size": 1376,
18
+ "norm_topk_prob": false,
19
+ "num_attention_heads": 16,
20
+ "num_experts": 60,
21
+ "num_experts_per_tok": 4,
22
+ "num_hidden_layers": 24,
23
+ "num_key_value_heads": 16,
24
+ "output_router_logits": false,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_theta": 1000000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "shared_expert_intermediate_size": 5504,
29
+ "sliding_window": 32768,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.40.0.dev0",
33
+ "use_cache": true,
34
+ "use_sliding_window": false,
35
+ "vocab_size": 151936
36
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1be3bccc46238822c2269449cb2e1ed96bda59d1cfbe47dc1026ff19c98baa41
3
+ size 1997571216
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4ac67f03363b5dba33973652c022f33647aae89345dc16749b66d41e72f1d0
3
+ size 1997874648
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619b628938361bbd3892e3a1fcaf98bc6e073dd303d444ff3cdc35bb0e8596c1
3
+ size 1998227536
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54555634b46740fc57cac1b4185b5c79ca062e68ef593d61b9c3fb2e36940b6d
3
+ size 1995236768
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35d22417363b055b031708deb50155e0b6e88e0a9ea1b3512d6927424a5d58f
3
+ size 1995236768
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c29b25bab1330965d41aff83b3831559eac0adec860b1e8901fec4de8fd7af
3
+ size 1995236808
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff4c2c56913f4196a87d709f3fa6fc80199010ca01b7e733da7d6aa4362097b
3
+ size 1989592960
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:368fe3b3ead6ada3526c6aa1b5a3878b42c3a6f24eb7bcd5ccc50979a4e174b0
3
+ size 1995237488
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907afeb1243c1f94c9e23ffc0ecb6acf90b150f70955c3c0ae195c387fe3955c
3
+ size 1995237112
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6087034e79f23e1a36290e7fcacb502c81f13dcc292e5d85c64e6695b1be72d7
3
+ size 1995237112
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4f2829453cc99211522d9ca28fd859f242b4729e201179824d410924c00e59
3
+ size 1995237128
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75abeedf6bd5dfb8fd43a6dba751876fa7b2ff9a731b07870c916b9ec037b2c9
3
+ size 1995229544
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278174deef95a37874ed1613f1f3f20a858acd8efdbbc0b9aa09e67c009ab77a
3
+ size 1995237128
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1ac96b1e7bb746fd1504896ff62aeb2473ca32ee8f6c5ab818886384217cdc
3
+ size 1465440456
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e43689c38b2f3349f79e0833012134ac89e6d9fa2b158285a9695852790abbb
3
+ size 622329984
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "left",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff