fbaldassarri
commited on
Commit
•
e725914
1
Parent(s):
9e0d8fa
Initial Upload
Browse files- README.md +87 -3
- config.json +64 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- quantize_config.json +25 -0
- special_tokens_map.json +34 -0
- tokenizer.json +0 -0
- tokenizer_config.json +155 -0
- vocab.json +0 -0
README.md
CHANGED
@@ -1,3 +1,87 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- de
|
5 |
+
- fr
|
6 |
+
- it
|
7 |
+
- pt
|
8 |
+
- hi
|
9 |
+
- es
|
10 |
+
- th
|
11 |
+
license: apache-2.0
|
12 |
+
library_name: transformers
|
13 |
+
tags:
|
14 |
+
- autoround
|
15 |
+
- auto-round
|
16 |
+
- intel-autoround
|
17 |
+
- gptq
|
18 |
+
- auto-gptq
|
19 |
+
- autogptq
|
20 |
+
- woq
|
21 |
+
- pytorch
|
22 |
+
- transformers
|
23 |
+
- intel
|
24 |
+
model_name: SmolLM2 135M Instruct
|
25 |
+
base_model: HuggingFaceTB/SmolLM2-135M-Instruct
|
26 |
+
inference: false
|
27 |
+
model_creator: HuggingFaceTB
|
28 |
+
pipeline_tag: text-generation
|
29 |
+
prompt_template: '{prompt}
|
30 |
+
'
|
31 |
+
quantized_by: fbaldassarri
|
32 |
+
---
|
33 |
+
|
34 |
+
## Model Information
|
35 |
+
|
36 |
+
Quantized version of [HuggingFaceTB/SmolLM2-135M-Instruct](HuggingFaceTB/SmolLM2-135M-Instruct) using torch.float32 for quantization tuning.
|
37 |
+
- 4 bits (INT4)
|
38 |
+
- group size = 128
|
39 |
+
- Asymmetrical Quantization
|
40 |
+
- Method AutoGPTQ
|
41 |
+
|
42 |
+
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.3
|
43 |
+
|
44 |
+
Note: this INT4 version of SmolLM2-135M-Instruct has been quantized to run inference through CPU.
|
45 |
+
|
46 |
+
## Replication Recipe
|
47 |
+
|
48 |
+
### Step 1 Install Requirements
|
49 |
+
|
50 |
+
I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
|
51 |
+
|
52 |
+
```
|
53 |
+
wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.3.tar.gz
|
54 |
+
tar -xvzf v0.4.3.tar.gz
|
55 |
+
cd auto-round-0.4.3
|
56 |
+
pip install -r requirements-cpu.txt --upgrade
|
57 |
+
```
|
58 |
+
|
59 |
+
### Step 2 Build Intel AutoRound wheel from sources
|
60 |
+
|
61 |
+
```
|
62 |
+
pip install -vvv --no-build-isolation -e .[cpu]
|
63 |
+
```
|
64 |
+
|
65 |
+
### Step 3 Script for Quantization
|
66 |
+
|
67 |
+
```
|
68 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
69 |
+
model_name = "HuggingFaceTB/SmolLM2-135M-Instruct"
|
70 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
71 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
72 |
+
from auto_round import AutoRound
|
73 |
+
bits, group_size, sym, device, amp = 4, 128, False, 'cpu', False
|
74 |
+
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
|
75 |
+
autoround.quantize()
|
76 |
+
output_dir = "./AutoRound/HuggingFaceTB_SmolLM2-135M-Instruct-auto_gptq-int4-gs128-asym"
|
77 |
+
autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
|
78 |
+
```
|
79 |
+
|
80 |
+
## License
|
81 |
+
|
82 |
+
[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)
|
83 |
+
|
84 |
+
## Disclaimer
|
85 |
+
|
86 |
+
This quantized model comes with no warrenty. It has been developed only for research purposes.
|
87 |
+
|
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
|
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 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 576,
|
13 |
+
"initializer_range": 0.041666666666666664,
|
14 |
+
"intermediate_size": 1536,
|
15 |
+
"is_llama_config": true,
|
16 |
+
"max_position_embeddings": 8192,
|
17 |
+
"mlp_bias": false,
|
18 |
+
"model_type": "llama",
|
19 |
+
"num_attention_heads": 9,
|
20 |
+
"num_hidden_layers": 30,
|
21 |
+
"num_key_value_heads": 3,
|
22 |
+
"pad_token_id": 2,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"quantization_config": {
|
25 |
+
"amp": false,
|
26 |
+
"autoround_version": "0.4.3",
|
27 |
+
"batch_size": 4,
|
28 |
+
"bits": 4,
|
29 |
+
"damp_percent": 0.01,
|
30 |
+
"data_type": "int",
|
31 |
+
"desc_act": false,
|
32 |
+
"enable_minmax_tuning": true,
|
33 |
+
"enable_norm_bias_tuning": false,
|
34 |
+
"enable_quanted_input": true,
|
35 |
+
"gradient_accumulate_steps": 1,
|
36 |
+
"group_size": 128,
|
37 |
+
"iters": 200,
|
38 |
+
"low_gpu_mem_usage": false,
|
39 |
+
"lr": 0.005,
|
40 |
+
"minmax_lr": 0.005,
|
41 |
+
"nsamples": 128,
|
42 |
+
"quant_method": "gptq",
|
43 |
+
"scale_dtype": "torch.float16",
|
44 |
+
"seqlen": 512,
|
45 |
+
"sym": false,
|
46 |
+
"to_quant_block_names": null,
|
47 |
+
"true_sequential": false
|
48 |
+
},
|
49 |
+
"rms_norm_eps": 1e-05,
|
50 |
+
"rope_interleaved": false,
|
51 |
+
"rope_scaling": null,
|
52 |
+
"rope_theta": 100000,
|
53 |
+
"tie_word_embeddings": true,
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers.js_config": {
|
56 |
+
"kv_cache_dtype": {
|
57 |
+
"fp16": "float16",
|
58 |
+
"q4f16": "float16"
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"transformers_version": "4.47.0",
|
62 |
+
"use_cache": true,
|
63 |
+
"vocab_size": 49152
|
64 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.47.0"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ddc2a2aee1a9e8ed3b79b83f0d31c07dca4dd050a15b71fcbad45ddb2863e2
|
3 |
+
size 169414824
|
quantize_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"sym": false,
|
5 |
+
"data_type": "int",
|
6 |
+
"enable_quanted_input": true,
|
7 |
+
"enable_minmax_tuning": true,
|
8 |
+
"seqlen": 512,
|
9 |
+
"batch_size": 4,
|
10 |
+
"scale_dtype": "torch.float16",
|
11 |
+
"lr": 0.005,
|
12 |
+
"minmax_lr": 0.005,
|
13 |
+
"gradient_accumulate_steps": 1,
|
14 |
+
"iters": 200,
|
15 |
+
"amp": false,
|
16 |
+
"nsamples": 128,
|
17 |
+
"low_gpu_mem_usage": false,
|
18 |
+
"to_quant_block_names": null,
|
19 |
+
"enable_norm_bias_tuning": false,
|
20 |
+
"autoround_version": "0.4.3",
|
21 |
+
"quant_method": "gptq",
|
22 |
+
"desc_act": false,
|
23 |
+
"true_sequential": false,
|
24 |
+
"damp_percent": 0.01
|
25 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_start|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<repo_name>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<reponame>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": "<file_sep>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": "<filename>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "<gh_stars>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<issue_start>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<issue_comment>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<issue_closed>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<jupyter_start>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"12": {
|
101 |
+
"content": "<jupyter_text>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"13": {
|
109 |
+
"content": "<jupyter_code>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"14": {
|
117 |
+
"content": "<jupyter_output>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"15": {
|
125 |
+
"content": "<jupyter_script>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"16": {
|
133 |
+
"content": "<empty_output>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
}
|
140 |
+
},
|
141 |
+
"additional_special_tokens": [
|
142 |
+
"<|im_start|>",
|
143 |
+
"<|im_end|>"
|
144 |
+
],
|
145 |
+
"bos_token": "<|im_start|>",
|
146 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
147 |
+
"clean_up_tokenization_spaces": false,
|
148 |
+
"eos_token": "<|im_end|>",
|
149 |
+
"extra_special_tokens": {},
|
150 |
+
"model_max_length": 2048,
|
151 |
+
"pad_token": "<|im_end|>",
|
152 |
+
"tokenizer_class": "GPT2Tokenizer",
|
153 |
+
"unk_token": "<|endoftext|>",
|
154 |
+
"vocab_size": 49152
|
155 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|