MaziyarPanahi commited on
Commit
010afdb
1 Parent(s): fab199d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - finetuned
5
+ - quantized
6
+ - 4-bit
7
+ - gptq
8
+ - transformers
9
+ - safetensors
10
+ - llama
11
+ - text-generation
12
+ - en
13
+ - license:mit
14
+ - model-index
15
+ - autotrain_compatible
16
+ - endpoints_compatible
17
+ - has_space
18
+ - text-generation-inference
19
+ - region:us
20
+ model_name: miqu-1-70b-sf-GPTQ
21
+ base_model: 152334H/miqu-1-70b-sf
22
+ inference: false
23
+ model_creator: 152334H
24
+ pipeline_tag: text-generation
25
+ quantized_by: MaziyarPanahi
26
+ ---
27
+ # Description
28
+ [MaziyarPanahi/miqu-1-70b-sf-GPTQ](https://huggingface.co/MaziyarPanahi/miqu-1-70b-sf-GPTQ) is a quantized (GPTQ) version of [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
29
+
30
+ ## How to use
31
+ ### Install the necessary packages
32
+
33
+ ```
34
+ pip install --upgrade accelerate auto-gptq transformers
35
+ ```
36
+
37
+ ### Example Python code
38
+
39
+
40
+ ```python
41
+ from transformers import AutoTokenizer, pipeline
42
+ from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
43
+ import torch
44
+
45
+ model_id = "MaziyarPanahi/miqu-1-70b-sf-GPTQ"
46
+
47
+ quantize_config = BaseQuantizeConfig(
48
+ bits=4,
49
+ group_size=128,
50
+ desc_act=False
51
+ )
52
+
53
+ model = AutoGPTQForCausalLM.from_quantized(
54
+ model_id,
55
+ use_safetensors=True,
56
+ device="cuda:0",
57
+ quantize_config=quantize_config)
58
+
59
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
60
+
61
+ pipe = pipeline(
62
+ "text-generation",
63
+ model=model,
64
+ tokenizer=tokenizer,
65
+ max_new_tokens=512,
66
+ temperature=0.7,
67
+ top_p=0.95,
68
+ repetition_penalty=1.1
69
+ )
70
+
71
+ outputs = pipe("What is a large language model?")
72
+ print(outputs[0]["generated_text"])
73
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "152334H/miqu-1-70b-sf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 32764,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 80,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1000000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50383d5abcbbcf01888ac04fe26a5d152ed6b21782c80f1220267168706307c6
3
+ size 36652345632
quantize_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.1,
5
+ "desc_act": false,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": null,
10
+ "model_file_base_name": null
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<unk>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }