Upload folder using huggingface_hub

#1
.DS_Store ADDED
Binary file (6.15 kB). View file
 
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ja
4
+ - en
5
+ license: mit
6
+ library_name: transformers
7
+ tags:
8
+ - mlx
9
+ ---
10
+
11
+ # mlx-community/stockmark-100b-8bit
12
+ This model was converted to MLX format from [`stockmark/stockmark-100b`]() using mlx-lm version **0.12.1**.
13
+ Refer to the [original model card](https://huggingface.co/stockmark/stockmark-100b) for more details on the model.
14
+ ## Use with mlx
15
+
16
+ ```bash
17
+ pip install mlx-lm
18
+ ```
19
+
20
+ ```python
21
+ from mlx_lm import load, generate
22
+
23
+ model, tokenizer = load("mlx-community/stockmark-100b-8bit")
24
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
25
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 9216,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 32256,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 72,
16
+ "num_hidden_layers": 88,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 2,
19
+ "pretraining_tp": 1,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 8
23
+ },
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.1",
30
+ "use_cache": true,
31
+ "vocab_size": 60416
32
+ }
model-00001-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4211a64027e9d24ad7f6cd50c166cf0a50f1c4adf02c33f77f2bc0923b9498
3
+ size 5294419504
model-00002-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d402b94ae73fb4eabf92771c87cf364fac49252b48367e3180b67c9cbaa0ae
3
+ size 5314473179
model-00003-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9a9b6941669c21b3635cc445b36f394edc7112e45b674f364188ff2f7aaa2c
3
+ size 5108957344
model-00004-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be2377f65b97342f11f9820ea9153cf36219a574a073583a284b7d18b49f189
3
+ size 5224229891
model-00005-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba557a1ae57f7b14fab595a50eccdfc9e5e575780290ae56c14898369625a83
3
+ size 5108957438
model-00006-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb27a7c46ec3e504e3ddd633873be51656b09918641a7e0bdcc1172dc9b59d6a
3
+ size 5224229887
model-00007-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f15fc2d1c00422dd7ad2aef0f6dde50880df0f0bda73a6a8fd9c9f1e8486355a
3
+ size 5108957422
model-00008-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0050e33dfc66a7ba0fc65c23413287f06049f9b64970b969257ed04acbf561c6
3
+ size 5224229859
model-00009-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e88c4c910f72ce9b5f8e88467efdba13e574420257d473a0b8a5a2baf6dcf5
3
+ size 5108957436
model-00010-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25240189523399273d9136ef88af856dac15f628d05164de6bcd13e91ba239c
3
+ size 5224229897
model-00011-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:901711a4c9d566d1139a58738f10af37499984c655735c9d0e72a96b16345076
3
+ size 5108957424
model-00012-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1c4ed7e5e1a4acb2818d70a1d49000c655f5ba2f8cdb4545497e3d27db0fcf
3
+ size 5224229901
model-00013-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9d6283a9281c205a706b7883bd98693e2adf54f83722a450ec49f83eef505a
3
+ size 5108957420
model-00014-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db7b280533f0283ae6bf9845956ea573541623b56aad099c3972acadef5af322
3
+ size 5224229893
model-00015-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae2d2d95b35a2465c2e699c9f7e5ecef1ff508c91c302261b66e5aab4f54290
3
+ size 5108957422
model-00016-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:845218d8d6fdfa1d6f0322db22a6f2d4aff30bf63ac121e7afae4cc745cbaa9d
3
+ size 5224229893
model-00017-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6775ea7f87cb38caeca2def59e0ad441b4735c5ac8d9d5423413231475fb82ca
3
+ size 5108957398
model-00018-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:456a3ed8b506554af8f20cc60bf0b418a199f83f250612e37be3ea3f34fe0a2a
3
+ size 5224229879
model-00019-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e18b31796a50dc51fc6612cf5b85dcbbd0903dabb0d67a05594d2a990f4575f
3
+ size 5108957420
model-00020-of-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae1bdbd15072e88bf111629d19c775b54f590c1b2a423156b7ecafc17c57c91
3
+ size 3835466480
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
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": "<pad>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
46
+ }