MLX
Safetensors
llama
prince-canuma commited on
Commit
e868ddd
1 Parent(s): 6189c61

Upload folder using huggingface_hub (#1)

Browse files

- 896054a55445b6fd7faa046797d5cf37dd5d8020554fbd3d5ab5608e3c3f91b6 (7c073a2f319531d8b08811d95da1fe55cf44aad9)
- a24e2a771ec12674e1810793926f47236d019bc54ffbf95cbca9295bd39a59f8 (d12ab612ff98ebce39c08a61fae599f8c5716d31)
- 3269cda7fa9d29806d67ae83a31e9f3bb15b1e75dfb7c3e353c59deefb3be5f5 (113fdd4117cac01733eb7598d5c16bdec2e75a29)
- d141789266aa976cfbcb9a0e3186277924cdaa86fc391e82c2d05d2800c25507 (b69e2180ae961e761427ee64887157d6dbcf8a4e)
- e3fac87ba6b7b7aa283d2237d31ab9dde00d237508b74bd30afcdd1cbf9003a0 (106a37e839015b260f0fdee1e166bf9f74af426a)
- 38aa040902b14b8030e65aa331fe8aa332ad4ed12286817e950e44c81b54ea39 (cf6d5c0a61ae465166610c7c920f0d85b61857f2)
- a96a75b7e55a922c08708a4f66f41c477aa203eb2247aba1fe13482e5c22c311 (018f4fa36fa7180aff0109d91dcf85ff1c0cebdc)
- 97e1b600b8d963a9c8852a1b0d6613fecaf400ed314dc154c72680fae738a4d0 (4b3b14123d698baecc1968ecaf75a5aa5ad8441f)

README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - mlx
5
+ ---
6
+
7
+ # mlx-community/Yi-1.5-34B-Chat-8bit
8
+
9
+ The Model [mlx-community/Yi-1.5-34B-Chat-8bit](https://huggingface.co/mlx-community/Yi-1.5-34B-Chat-8bit) was converted to MLX format from [01-ai/Yi-1.5-34B-Chat](https://huggingface.co/01-ai/Yi-1.5-34B-Chat) using mlx-lm version **0.13.0**.
10
+
11
+ ## Use with mlx
12
+
13
+ ```bash
14
+ pip install mlx-lm
15
+ ```
16
+
17
+ ```python
18
+ from mlx_lm import load, generate
19
+
20
+ model, tokenizer = load("mlx-community/Yi-1.5-34B-Chat-8bit")
21
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
22
+ ```
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": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 7168,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 56,
16
+ "num_hidden_layers": 60,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "quantization": {
21
+ "group_size": 64,
22
+ "bits": 8
23
+ },
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_scaling": null,
26
+ "rope_theta": 5000000.0,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.0",
30
+ "use_cache": false,
31
+ "vocab_size": 64000
32
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dbe5861dd72e7647efac03ee209b8862aab4ffd0e19af7620d65290b6800d52
3
+ size 5354117230
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd55596e5138164fedc16a57521469e6f369f012b5b1c2140baf5eca7e0b755
3
+ size 5334650055
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3454085ef901bf74cfacd8523d945835d700b9c53c79b29b920153789d15e02f
3
+ size 5334650069
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9091d7018bd4e0ed17cd0817c737228efa1fc4265c7b25c809ddf3749a1de3
3
+ size 5334650063
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c95e51984c1836059b3a32e87cafff602dbb9a8dacefc41d6ebfb6b94fc273
3
+ size 5334650069
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32dcecd844ffbea9295fc7036707515a9844cf48913ab60bf170edb197233cce
3
+ size 5334650073
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8046d083dd222aa059dd914e704c5c3a7e01d02a19c188c41476977480534ee5
3
+ size 4511829028
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": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|startoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|endoftext|>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "7": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ }
38
+ },
39
+ "bos_token": "<|startoftext|>",
40
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
41
+ "clean_up_tokenization_spaces": false,
42
+ "eos_token": "<|im_end|>",
43
+ "legacy": true,
44
+ "model_max_length": 4096,
45
+ "pad_token": "<unk>",
46
+ "padding_side": "right",
47
+ "sp_model_kwargs": {},
48
+ "spaces_between_special_tokens": false,
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "LlamaTokenizer",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": false
53
+ }