prince-canuma commited on
Commit
6f7d783
1 Parent(s): 950406f

Upload folder using huggingface_hub (#1)

Browse files

- 3ad7b429e38a8197b5944da14227ccc07ba47cd961c15401b976d3853bc83ac3 (8153cda67382b036d767887dc0da500ed46ba77f)
- 685b1737f3ef6de93267d01bfbc7ef9a3ca265b84bfdbd383988b6af0bb4453c (521f7957b5bf89641ae017f1f37a7248758b946c)
- 316fbfe33bc0de2710b740416508cdce1627e8bf07f22ddf481890a69826ae52 (ddb134229216b5116bddf84f457425712a7797ce)
- 604822d9d92dfd51e06ff691e30d290b2d3adef3f32d9ed8b61460d5f0ab33a5 (ac2a35eb767cc404c72b8e40452496d46ada5c1e)
- b5af0887219e8de9ed3f2002e84a89fff626bba37aca7b563422bac0acbbfa9e (fa961613d75604b123686e30f99cb901bddd0f97)
- 510863c7c6ae61b56ecd800c679fb10c88b2806d6a604b3d9b963cbc2e55bd89 (17f51560ca9b77ef8a4bc3248990119cda3598bc)
- fd023a8a4c85968af51224b8a0136ff128554efb43b962b62c37d549854d8ee0 (0b2bf0711bd28af3373b7071a52b8e3ffe1e18c0)
- 3c24b8241aaf9eadbdcbecafd288605b1db79619fc2765b2768871b52922f1e8 (25cc9fe93e83d7428b58dfc0d323eca84a678e4d)
- fcb0500df151cdad2fde9230b7521f780b6fc6053af090969a9666eec1a91006 (c3136caa0a088ec02787e1e3f2134afd1edcbdd3)
- c96a4a6724a288fc4a8cac11b6af8cb83f2d454f45e42bfb16e074b75cbc7b8f (a3ee23972d65f69d72c9a10a54b8f8f7ac287c67)
- 01c78546ff6dfbf0a50172eb1f224cde8b9ad00154f97a1470abba58c3882515 (eb5d279ea3a385807b2a64cf2448b5aebfa512e8)
- f0e5ff9968b29b1cc9c8e91f97d95d54ed66953582cbd64b7bc161d08960c56a (ec9ee2c141b622bb4e83323646231364df7eba69)
- 005c1948c4cda66f333d46e138678721b0db0d16cc848de53a326725f2558eb7 (26cf9ff8d0e66bd72d90fbfea873288c154f7adf)
- e5af6f41165cf82e25e66e223306cc516b30c1a210eeacd8c75eab9fd5c34b59 (09df40122a5f575645f79de6fdb41b20ebc236b4)
- 2d12c5f5fbf7708f8c6822ce25ba5eb8c0264d049e2bf4e1a5d091ccf07bce1b (f4615941bf2f0cf9beba9a38cd6d647fb69e757e)
- 28b4af0dedbf9953b2aa39ba337209d25fa81bd23762ed191e916a5149fc6094 (1b3b4f4f51f1457009f1116381f653dbb874dee5)

README.md ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: other
5
+ tags:
6
+ - chat
7
+ - mlx
8
+ license_name: tongyi-qianwen
9
+ license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
10
+ pipeline_tag: text-generation
11
+ ---
12
+
13
+ # mlx-community/Qwen2-72B-Instruct-8bit
14
+
15
+ The Model [mlx-community/Qwen2-72B-Instruct-8bit](https://huggingface.co/mlx-community/Qwen2-72B-Instruct-8bit) was converted to MLX format from [Qwen/Qwen2-72B-Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct) using mlx-lm version **0.14.3**.
16
+
17
+ ## Use with mlx
18
+
19
+ ```bash
20
+ pip install mlx-lm
21
+ ```
22
+
23
+ ```python
24
+ from mlx_lm import load, generate
25
+
26
+ model, tokenizer = load("mlx-community/Qwen2-72B-Instruct-8bit")
27
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
28
+ ```
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 29568,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 80,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "quantization": {
19
+ "group_size": 64,
20
+ "bits": 8
21
+ },
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_theta": 1000000.0,
24
+ "sliding_window": 131072,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.40.1",
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 152064
31
+ }
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 sha256:1c7ff05f66ed5e820e53ea642458b386648e2e28efa5ca8ab48788abd75d2cc5
3
+ size 5214291418
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aafa44d88e27340c2909849d26e99a64c10abc9eb316ef778e8a16e2e57e124
3
+ size 5177560124
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0a35d0461e049a430e5a43ec904bdb94f6507c743644b1b99e791393f5f760
3
+ size 5338047575
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccad12e4986b998d7e590b056827af563bbc690f1b444e55b61db598d33d0366
3
+ size 5338047581
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eeb830b3b07f941ac37a235a4501a5b8c54560765dddbfa18814603748c4431
3
+ size 5177560270
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84dc724bd195de635e2d9619acbadd5cf922cbfe70c056958c42c1a2c0f14651
3
+ size 5338047562
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1ce5106948ebaf14927f9d11a47f8f375004c203196c6d159b8b679b807a7b9
3
+ size 5338047557
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a5f3687b6b337692bc3e0cb4164f0bae5ea03a2e7ac2ea50fb65d252778234
3
+ size 5177560278
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e342a7d578217788d524644c59c1f0a775d2fd87c8ae058fa4aa423a4dfd91dd
3
+ size 5338047594
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714621457f386097ffec68fee22f7e41db0045ff53fd433355fe06a730235da7
3
+ size 5338047549
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca33c17ebb5490e5194dcc0eb320dd95aed7c79416a45f09e06482cf2441ab8d
3
+ size 5177560280
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8de4ec0b61f4b0d7ba88dff684a3c6b32b651ad1e66336ca3ca56f284781c3fb
3
+ size 5338047560
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d0971a70854b9c6b19b1da48788f2dad54c3c21ddded3da04f970d4a66c086
3
+ size 5338047535
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd497fcb104702874e955169bc233d4471c04b069d0df1ff26658eaf3901f554
3
+ size 5177560290
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef8ccda99a8bce9dc4f1ca32e85fe4d46b1a797547835a655e6caf50e62cff9
3
+ size 3446110912
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": "<|im_end|>",
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.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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 131072,
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