Hugging Face's logo

webAI-Official
/
TwIL-LM

Text Generation
PEFT
GGUF
English
llama
formal-logic
reasoning
lora
llama.cpp
smollm2
twil-lm
conversational
Model card Files
xet
 Community
1
cutterdalton-webai commited on
Commit
c983233
·
verified ·
1 Parent(s): 874a457

Upload 9 files

Browse files

Initial commit of weights and tokenized adapter of v1 model. Model based on pretrained SmolLM2-1.7B.

Files changed (10) hide show
  1. .gitattributes +4 -0
  2. merged/chat_template.jinja +6 -0
  3. merged/config.json +43 -0
  4. merged/generation_config.json +10 -0
  5. merged/smollm2-lorav1-ps-merged-Q4_K_M.gguf +3 -0
  6. merged/smollm2-lorav1-ps-merged-Q5_K_M.gguf +3 -0
  7. merged/smollm2-lorav1-ps-merged-Q8_0.gguf +3 -0
  8. merged/smollm2-lorav1-ps-merged-f16.gguf +3 -0
  9. merged/tokenizer.json +0 -0
  10. merged/tokenizer_config.json +157 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ merged/smollm2-lorav1-ps-merged-f16.gguf filter=lfs diff=lfs merge=lfs -text
37
+ merged/smollm2-lorav1-ps-merged-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ merged/smollm2-lorav1-ps-merged-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ merged/smollm2-lorav1-ps-merged-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
merged/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
merged/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "torch_dtype": "bfloat16",
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 24,
20
+ "num_key_value_heads": 32,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_parameters": {
25
+ "rope_theta": 130000,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": true,
29
+ "transformers.js_config": {
30
+ "torch_dtype": "q4",
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ },
35
+ "use_external_data_format": {
36
+ "model.onnx": true,
37
+ "model_fp16.onnx": true
38
+ }
39
+ },
40
+ "unsloth_version": "2026.7.4",
41
+ "use_cache": true,
42
+ "vocab_size": 49152
43
+ }
merged/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "max_length": 8192,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "5.5.0"
10
+ }
merged/smollm2-lorav1-ps-merged-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185abb5a630ba760b0abd4f4f886d74b1c193d6c8350e9c2bab88355ba38bcf9
3
+ size 1055609376
merged/smollm2-lorav1-ps-merged-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add126e1a9dc5d4c4c01fb273df5e111a2c54f711684b22d2f56a8f43658006d
3
+ size 1225478688
merged/smollm2-lorav1-ps-merged-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2797be007757c22d8fe9b87557946e4b3d40616718d5cc12a692d1ed9792cc
3
+ size 1820414496
merged/smollm2-lorav1-ps-merged-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec8fc823f1d67b460b39ed402efdd43b7c1f89c1c64d1a32d0a63a4d8c8cca4
3
+ size 3424735776
merged/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
merged/tokenizer_config.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>"
11
+ ],
12
+ "is_local": false,
13
+ "model_max_length": 8192,
14
+ "pad_token": "<|endoftext|>",
15
+ "padding_side": "left",
16
+ "tokenizer_class": "GPT2Tokenizer",
17
+ "unk_token": "<|endoftext|>",
18
+ "vocab_size": 49152,
19
+ "added_tokens_decoder": {
20
+ "0": {
21
+ "content": "<|endoftext|>",
22
+ "single_word": false,
23
+ "lstrip": false,
24
+ "rstrip": false,
25
+ "normalized": false,
26
+ "special": true
27
+ },
28
+ "1": {
29
+ "content": "<|im_start|>",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": false,
34
+ "special": true
35
+ },
36
+ "2": {
37
+ "content": "<|im_end|>",
38
+ "single_word": false,
39
+ "lstrip": false,
40
+ "rstrip": false,
41
+ "normalized": false,
42
+ "special": true
43
+ },
44
+ "3": {
45
+ "content": "<repo_name>",
46
+ "single_word": false,
47
+ "lstrip": false,
48
+ "rstrip": false,
49
+ "normalized": false,
50
+ "special": true
51
+ },
52
+ "4": {
53
+ "content": "<reponame>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ "5": {
61
+ "content": "<file_sep>",
62
+ "single_word": false,
63
+ "lstrip": false,
64
+ "rstrip": false,
65
+ "normalized": false,
66
+ "special": true
67
+ },
68
+ "6": {
69
+ "content": "<filename>",
70
+ "single_word": false,
71
+ "lstrip": false,
72
+ "rstrip": false,
73
+ "normalized": false,
74
+ "special": true
75
+ },
76
+ "7": {
77
+ "content": "<gh_stars>",
78
+ "single_word": false,
79
+ "lstrip": false,
80
+ "rstrip": false,
81
+ "normalized": false,
82
+ "special": true
83
+ },
84
+ "8": {
85
+ "content": "<issue_start>",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": false,
90
+ "special": true
91
+ },
92
+ "9": {
93
+ "content": "<issue_comment>",
94
+ "single_word": false,
95
+ "lstrip": false,
96
+ "rstrip": false,
97
+ "normalized": false,
98
+ "special": true
99
+ },
100
+ "10": {
101
+ "content": "<issue_closed>",
102
+ "single_word": false,
103
+ "lstrip": false,
104
+ "rstrip": false,
105
+ "normalized": false,
106
+ "special": true
107
+ },
108
+ "11": {
109
+ "content": "<jupyter_start>",
110
+ "single_word": false,
111
+ "lstrip": false,
112
+ "rstrip": false,
113
+ "normalized": false,
114
+ "special": true
115
+ },
116
+ "12": {
117
+ "content": "<jupyter_text>",
118
+ "single_word": false,
119
+ "lstrip": false,
120
+ "rstrip": false,
121
+ "normalized": false,
122
+ "special": true
123
+ },
124
+ "13": {
125
+ "content": "<jupyter_code>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ "14": {
133
+ "content": "<jupyter_output>",
134
+ "single_word": false,
135
+ "lstrip": false,
136
+ "rstrip": false,
137
+ "normalized": false,
138
+ "special": true
139
+ },
140
+ "15": {
141
+ "content": "<jupyter_script>",
142
+ "single_word": false,
143
+ "lstrip": false,
144
+ "rstrip": false,
145
+ "normalized": false,
146
+ "special": true
147
+ },
148
+ "16": {
149
+ "content": "<empty_output>",
150
+ "single_word": false,
151
+ "lstrip": false,
152
+ "rstrip": false,
153
+ "normalized": false,
154
+ "special": true
155
+ }
156
+ }
157
+ }