Hugging Face's logo

Qwen
/
Qwen1.5-72B-Chat-AWQ

Text Generation
Transformers
Safetensors
English
qwen2
chat
conversational
text-generation-inference
4-bit precision
awq
Model card Files
xet
 Community
2
JustinLin610 commited on
Commit
6909dcb
·
verified ·
1 Parent(s): 1c01aba

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. config.json +35 -0
  2. generation_config.json +13 -0
  3. merges.txt +0 -0
  4. model-00001-of-00011.safetensors +3 -0
  5. model-00002-of-00011.safetensors +3 -0
  6. model-00003-of-00011.safetensors +3 -0
  7. model-00004-of-00011.safetensors +3 -0
  8. model-00005-of-00011.safetensors +3 -0
  9. model-00006-of-00011.safetensors +3 -0
  10. model-00007-of-00011.safetensors +3 -0
  11. model-00008-of-00011.safetensors +3 -0
  12. model-00009-of-00011.safetensors +3 -0
  13. model-00010-of-00011.safetensors +3 -0
  14. model-00011-of-00011.safetensors +3 -0
  15. model.safetensors.index.json +0 -0
  16. quant_config.json +7 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +43 -0
  19. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 24576,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 70,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 64,
18
+ "quantization_config": {
19
+ "bits": 4,
20
+ "group_size": 128,
21
+ "modules_to_not_convert": null,
22
+ "quant_method": "awq",
23
+ "version": "gemm",
24
+ "zero_point": true
25
+ },
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": 32768,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.37.0",
32
+ "use_cache": true,
33
+ "use_sliding_window": false,
34
+ "vocab_size": 152064
35
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.37.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d745105ce20d1c8c3aa060d17c780fd35cebb261809aa565ba522c14e33a065
3
+ size 3990923640
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c55beb6f8005b5c3eec5ce3a3c652df813dc4a7170fb14c6125e3c2ddbdb6f4
3
+ size 3975357104
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785fe8f86df19c6c8daa7d77f7b8a1445c080f76d10720e4245ad983934a90b7
3
+ size 3940475976
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251852f07739c192fdd0a959ab4f1ce402c6ca1970a7d6dcbf4b3d50c14b2c68
3
+ size 3975390968
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5a850f8316f6ac82ae0cc45446d02d4592d9a96a1739bffa098a8589ca8d54
3
+ size 3975390968
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf6ab2d24d61142eb4e630b873134380d20e314b4aaaa5b848dcc361f1a55f1
3
+ size 3975357280
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbc834e8ee5d6897d291cac97370bfaf02450dd9859a3892481d4e90da4e62a
3
+ size 3940475976
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dba54269ee8a81ad4edb689709bca07fd7711b764a6e137389f7823ddf76fc97
3
+ size 3975390968
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5d58a9d5cfde73a4884f94c7e01758021c5aa944f610123affb601f343e8a51
3
+ size 3975390968
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce920a7ca20af620074ef4e54f7efa13a7f267ee3d57fdb06704e9f580ecabeb
3
+ size 3033828032
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f96e68ba413eaf6af6e576fd92f3fe914e2b19d2363657dbe36ea46628067c60
3
+ size 2491416704
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quant_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "zero_point": true,
3
+ "q_group_size": 128,
4
+ "w_bit": 4,
5
+ "version": "GEMM",
6
+ "modules_to_not_convert": null
7
+ }
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_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": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff