andito HF staff commited on
Commit
251d657
1 Parent(s): 3813739

Upload folder using huggingface_hub (#1)

Browse files

- 0e64524199aa27b02babf05db4de228f475644f16a8708862af202b03bec9b6b (0438ae3fda4b8745e11b093e12417145cca117ff)

README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM-360M
3
+ datasets:
4
+ - Magpie-Align/Magpie-Pro-300K-Filtered
5
+ - bigcode/self-oss-instruct-sc2-exec-filter-50k
6
+ - teknium/OpenHermes-2.5
7
+ - HuggingFaceTB/everyday-conversations-llama3.1-2k
8
+ language:
9
+ - en
10
+ library_name: transformers
11
+ license: apache-2.0
12
+ tags:
13
+ - alignment-handbook
14
+ - trl
15
+ - sft
16
+ - mlx
17
+ ---
18
+
19
+ # mlx-community/SmolLM-360M-Instruct
20
+
21
+ The Model [mlx-community/SmolLM-360M-Instruct](https://huggingface.co/mlx-community/SmolLM-360M-Instruct) was converted to MLX format from [HuggingFaceTB/SmolLM-360M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct) using mlx-lm version **0.17.0**.
22
+
23
+ ## Use with mlx
24
+
25
+ ```bash
26
+ pip install mlx-lm
27
+ ```
28
+
29
+ ```python
30
+ from mlx_lm import load, generate
31
+
32
+ model, tokenizer = load("mlx-community/SmolLM-360M-Instruct")
33
+ response = generate(model, tokenizer, prompt="hello", verbose=True)
34
+ ```
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 960,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2560,
13
+ "max_position_embeddings": 2048,
14
+ "mlp_bias": false,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 15,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 5,
19
+ "pad_token_id": 2,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "vocab_size": 49152
29
+ }
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:d9f9d39cc25d50591810aeb781c3f943c54423d7677eda38baf324e40d03e17d
3
+ size 723674525
model.safetensors.index.json ADDED
@@ -0,0 +1,297 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 723642240
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
97
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
98
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
99
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
100
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
101
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
102
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
103
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
104
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
105
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
106
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
107
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
108
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
109
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
110
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
111
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
112
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
113
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
114
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
115
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
116
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
117
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
118
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
119
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
120
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
121
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
122
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
123
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
124
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
125
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
126
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
127
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
128
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
129
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
130
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
131
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
132
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
133
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
134
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
135
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
136
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
137
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
138
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
139
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
140
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
141
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
142
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
143
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
144
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
145
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
146
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
147
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
148
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
149
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
150
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
151
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
152
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
153
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
154
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
155
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
156
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
157
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
158
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
159
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
160
+ "model.layers.24.input_layernorm.weight": "model.safetensors",
161
+ "model.layers.24.mlp.down_proj.weight": "model.safetensors",
162
+ "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
163
+ "model.layers.24.mlp.up_proj.weight": "model.safetensors",
164
+ "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
165
+ "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
166
+ "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
167
+ "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
168
+ "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
169
+ "model.layers.25.input_layernorm.weight": "model.safetensors",
170
+ "model.layers.25.mlp.down_proj.weight": "model.safetensors",
171
+ "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
172
+ "model.layers.25.mlp.up_proj.weight": "model.safetensors",
173
+ "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
174
+ "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
175
+ "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
176
+ "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
177
+ "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
178
+ "model.layers.26.input_layernorm.weight": "model.safetensors",
179
+ "model.layers.26.mlp.down_proj.weight": "model.safetensors",
180
+ "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
181
+ "model.layers.26.mlp.up_proj.weight": "model.safetensors",
182
+ "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
183
+ "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
184
+ "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
185
+ "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
186
+ "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
187
+ "model.layers.27.input_layernorm.weight": "model.safetensors",
188
+ "model.layers.27.mlp.down_proj.weight": "model.safetensors",
189
+ "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
190
+ "model.layers.27.mlp.up_proj.weight": "model.safetensors",
191
+ "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
192
+ "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
193
+ "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
194
+ "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
195
+ "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
196
+ "model.layers.28.input_layernorm.weight": "model.safetensors",
197
+ "model.layers.28.mlp.down_proj.weight": "model.safetensors",
198
+ "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
199
+ "model.layers.28.mlp.up_proj.weight": "model.safetensors",
200
+ "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
201
+ "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
202
+ "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
203
+ "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
204
+ "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
205
+ "model.layers.29.input_layernorm.weight": "model.safetensors",
206
+ "model.layers.29.mlp.down_proj.weight": "model.safetensors",
207
+ "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
208
+ "model.layers.29.mlp.up_proj.weight": "model.safetensors",
209
+ "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
210
+ "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
211
+ "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
212
+ "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
213
+ "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
214
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
215
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
216
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
217
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
218
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
219
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
220
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
221
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
223
+ "model.layers.30.input_layernorm.weight": "model.safetensors",
224
+ "model.layers.30.mlp.down_proj.weight": "model.safetensors",
225
+ "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
226
+ "model.layers.30.mlp.up_proj.weight": "model.safetensors",
227
+ "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
228
+ "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
229
+ "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
230
+ "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
231
+ "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
232
+ "model.layers.31.input_layernorm.weight": "model.safetensors",
233
+ "model.layers.31.mlp.down_proj.weight": "model.safetensors",
234
+ "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
235
+ "model.layers.31.mlp.up_proj.weight": "model.safetensors",
236
+ "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
237
+ "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
238
+ "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
239
+ "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
240
+ "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
241
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
242
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
243
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
244
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
245
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
246
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
247
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
248
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
249
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
250
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
251
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
252
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
253
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
254
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
255
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
256
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
257
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
258
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
259
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
260
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
261
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
262
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
263
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
264
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
265
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
266
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
267
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
268
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
269
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
270
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
271
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
272
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
273
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
274
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
275
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
276
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
277
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
278
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
279
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
280
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
281
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
282
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
283
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
284
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
285
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
286
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
287
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
288
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
289
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
290
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
291
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
292
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
293
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
294
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
295
+ "model.norm.weight": "model.safetensors"
296
+ }
297
+ }
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
+ }
test_prompts.py ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import AutoModelForCausalLM, AutoTokenizer
2
+
3
+ BASE_PATH = "/fsx/loubna/projects/alignment-handbook/recipes/cosmo2/sft/data"
4
+ TEMPERATURE = 0.2
5
+ TOP_P = 0.9
6
+
7
+ CHECKPOINT = "loubnabnl/smollm-350M-instruct-add-basics"
8
+
9
+ print(f"💾 Loading the model and tokenizer: {CHECKPOINT}...")
10
+ device = "cuda"
11
+ tokenizer = AutoTokenizer.from_pretrained(CHECKPOINT)
12
+ model_s = AutoModelForCausalLM.from_pretrained(CHECKPOINT).to(device)
13
+
14
+ print("🧪 Testing single-turn conversations...")
15
+ L = [
16
+ "Hi",
17
+ "Hello",
18
+ "Tell me a joke",
19
+ "Who are you?",
20
+ "What's your name?",
21
+ "How do I make pancakes?",
22
+ "Can you tell me what is gravity?",
23
+ "What is the capital of Morocco?",
24
+ "What's 2+2?",
25
+ "Hi, what is 2+1?",
26
+ "What's 3+5?",
27
+ "Write a poem about Helium",
28
+ "Hi, what are some popular dishes from Japan?",
29
+ ]
30
+
31
+
32
+ for i in range(len(L)):
33
+ print(f"🔮 {L[i]}")
34
+ messages = [{"role": "user", "content": L[i]}]
35
+ input_text = tokenizer.apply_chat_template(messages, tokenize=False)
36
+ inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
37
+ outputs = model_s.generate(
38
+ inputs, max_new_tokens=200, top_p=TOP_P, do_sample=True, temperature=TEMPERATURE
39
+ )
40
+ with open(
41
+ f"{BASE_PATH}/{CHECKPOINT.split('/')[-1]}_temp_{TEMPERATURE}_topp{TOP_P}.txt",
42
+ "a",
43
+ ) as f:
44
+ f.write("=" * 50 + "\n")
45
+ f.write(tokenizer.decode(outputs[0]))
46
+ f.write("\n")
47
+
48
+
49
+ print("🧪 Now testing multi-turn conversations...")
50
+ # Multi-turn conversations
51
+ messages_1 = [
52
+ {"role": "user", "content": "Hi"},
53
+ {"role": "assistant", "content": "Hello! How can I help you today?"},
54
+ {"role": "user", "content": "What's 2+2?"},
55
+ ]
56
+ messages_2 = [
57
+ {"role": "user", "content": "Hi"},
58
+ {"role": "assistant", "content": "Hello! How can I help you today?"},
59
+ {"role": "user", "content": "What's 2+2?"},
60
+ {"role": "assistant", "content": "4"},
61
+ {"role": "user", "content": "Why?"},
62
+ ]
63
+ messages_3 = [
64
+ {"role": "user", "content": "Who are you?"},
65
+ {"role": "assistant", "content": "I am an AI assistant. How can I help you today?"},
66
+ {"role": "user", "content": "What's your name?"},
67
+ ]
68
+ messages_4 = [
69
+ {"role": "user", "content": "Tell me a joke"},
70
+ {"role": "assistant", "content": "Sure! Why did the tomato turn red?"},
71
+ {"role": "user", "content": "Why?"},
72
+ ]
73
+ messages_5 = [
74
+ {"role": "user", "content": "Can you tell me what is gravity?"},
75
+ {
76
+ "role": "assistant",
77
+ "content": "Sure! Gravity is a force that attracts objects toward each other. It is what keeps us on the ground and what makes things fall.",
78
+ },
79
+ {"role": "user", "content": "Who discovered it?"},
80
+ ]
81
+ messages_6 = [
82
+ {"role": "user", "content": "How do I make pancakes?"},
83
+ {
84
+ "role": "assistant",
85
+ "content": "Sure! Here is a simple recipe for pancakes: Ingredients: 1 cup flour, 1 cup milk, 1 egg, 1 tbsp sugar, 1 tsp baking powder, 1/2 tsp salt. Instructions: 1. Mix all the dry ingredients together in a bowl. 2. Add the milk and egg and mix until smooth. 3. Heat a non-stick pan over medium heat. 4. Pour 1/4 cup of batter onto the pan. 5. Cook until bubbles form on the surface, then flip and cook for another minute. 6. Serve with your favorite toppings.",
86
+ },
87
+ {"role": "user", "content": "What are some popular toppings?"},
88
+ ]
89
+
90
+ L = [messages_1, messages_2, messages_3, messages_4, messages_5, messages_6]
91
+
92
+ for i in range(len(L)):
93
+ input_text = tokenizer.apply_chat_template(L[i], tokenize=False)
94
+ inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
95
+ outputs = model_s.generate(
96
+ inputs, max_new_tokens=200, top_p=TOP_P, do_sample=True, temperature=TEMPERATURE
97
+ )
98
+ with open(
99
+ f"{BASE_PATH}/{CHECKPOINT.split('/')[-1]}_temp_{TEMPERATURE}_topp{TOP_P}_MT.txt",
100
+ "a",
101
+ ) as f:
102
+ f.write("=" * 50 + "\n")
103
+ f.write(tokenizer.decode(outputs[0]))
104
+ f.write("\n")
105
+
106
+ print("🔥 Done!")
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 %}{{'<|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
+ "model_max_length": 2048,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff