ThomasTheMaker commited on
Commit
9d4db62
·
verified ·
1 Parent(s): 0952dfc

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +28 -0
  2. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json +3 -0
  3. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +39 -0
  4. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  5. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  6. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  7. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +28 -0
  8. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  9. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +171 -0
  10. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  11. unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  12. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json +3 -0
  13. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +39 -0
  14. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  15. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  16. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  17. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +28 -0
  18. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  19. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +171 -0
  20. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  21. unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  22. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json +3 -0
  23. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +39 -0
  24. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  25. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  26. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  27. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +28 -0
  28. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  29. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +171 -0
  30. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  31. unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  32. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json +3 -0
  33. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +39 -0
  34. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  35. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  36. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  37. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +28 -0
  38. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  39. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +171 -0
  40. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  41. unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  42. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json +3 -0
  43. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +39 -0
  44. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  45. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  46. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  47. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +28 -0
  48. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  49. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +171 -0
  50. unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
.gitattributes CHANGED
@@ -77,3 +77,31 @@ unsloth_SmolLM-135M-Instruct_6_layers_2_8_Open-Orca_SlimOrca_8000_ReplaceMe_lsts
77
  unsloth_SmolLM-135M-Instruct_7_layers_2_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
78
  unsloth_SmolLM-135M-Instruct_8_layers_2_10_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
79
  unsloth_SmolLM-135M-Instruct_9_layers_2_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  unsloth_SmolLM-135M-Instruct_7_layers_2_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
78
  unsloth_SmolLM-135M-Instruct_8_layers_2_10_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
79
  unsloth_SmolLM-135M-Instruct_9_layers_2_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
80
+ unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
81
+ unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
82
+ unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
83
+ unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
84
+ unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
85
+ unsloth_SmolLM2-135M-Instruct_15_layers_4_19_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
86
+ unsloth_SmolLM2-135M-Instruct_16_layers_3_19_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
87
+ unsloth_SmolLM2-135M-Instruct_17_layers_2_19_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
88
+ unsloth_SmolLM2-135M-Instruct_18_layers_4_22_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
89
+ unsloth_SmolLM2-135M-Instruct_19_layers_4_23_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
90
+ unsloth_SmolLM2-135M-Instruct_20_layers_3_23_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
91
+ unsloth_SmolLM2-135M-Instruct_21_layers_2_23_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
92
+ unsloth_SmolLM2-135M-Instruct_22_layers_2_24_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
93
+ unsloth_SmolLM2-135M-Instruct_23_layers_1_24_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
94
+ unsloth_SmolLM2-135M-Instruct_24_layers_2_26_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
95
+ unsloth_SmolLM2-135M-Instruct_25_layers_2_27_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
96
+ unsloth_SmolLM2-135M-Instruct_26_layers_1_27_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
97
+ unsloth_SmolLM2-135M-Instruct_27_layers_1_28_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
98
+ unsloth_SmolLM2-135M-Instruct_28_layers_2_30_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
99
+ unsloth_SmolLM2-135M-Instruct_29_layers_1_30_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
100
+ unsloth_SmolLM2-135M-Instruct_2_layers_3_5_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
101
+ unsloth_SmolLM2-135M-Instruct_3_layers_2_5_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
102
+ unsloth_SmolLM2-135M-Instruct_4_layers_2_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
103
+ unsloth_SmolLM2-135M-Instruct_5_layers_2_7_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
104
+ unsloth_SmolLM2-135M-Instruct_6_layers_3_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
105
+ unsloth_SmolLM2-135M-Instruct_7_layers_2_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
106
+ unsloth_SmolLM2-135M-Instruct_8_layers_2_10_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
107
+ unsloth_SmolLM2-135M-Instruct_9_layers_2_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/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": 20,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 49152,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 49153
39
+ }
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 8192,
6
+ "pad_token_id": 49152,
7
+ "transformers_version": "4.46.3"
8
+ }
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a7e8ef2e13e8593144f9c2c8458e9dac660ac2b4285dfb73503f16fe9009d6
3
+ size 198249608
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_10_layers_2_12_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f58753f6bd0e2c2db081686c60a70805ca675c117e262b2d7e5889ddf3d122
3
+ size 2656281
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/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": 19,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 49152,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 49153
39
+ }
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 8192,
6
+ "pad_token_id": 49152,
7
+ "transformers_version": "4.46.3"
8
+ }
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dabcae39c6e9ce043c38f35eb44197947768304f23af1a3abe0e9d8e94b78f8
3
+ size 191168400
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d45b4ca10cac1766ae4eb9059e88e6822f9602976c36515101318d1b776a46
3
+ size 2656281
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/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": 18,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 49152,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 49153
39
+ }
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 8192,
6
+ "pad_token_id": 49152,
7
+ "transformers_version": "4.46.3"
8
+ }
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:467cc28bf3121adb6ec4d6ea0bb09d9f7704504db8b5d77374c898fdc9c5aa39
3
+ size 184087192
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_12_layers_2_14_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c13d0ea8620a6de703ad7f2f73605785f4bea9f111afb431d15f01a0ac788e
3
+ size 2656281
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/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": 17,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 49152,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 49153
39
+ }
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 8192,
6
+ "pad_token_id": 49152,
7
+ "transformers_version": "4.46.3"
8
+ }
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3898f842dd1d25804b1031d68ea2762ce6b402a1c15e2ce19e8c99cb09b5854e
3
+ size 177005984
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a43c959bafb8bb221dda3f63087d811a75d8d3b909bcc24465d69aa8b41e7a3
3
+ size 2656281
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/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": 16,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 49152,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.46.3",
37
+ "use_cache": true,
38
+ "vocab_size": 49153
39
+ }
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 8192,
6
+ "pad_token_id": 49152,
7
+ "transformers_version": "4.46.3"
8
+ }
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f981d77381ebe7c6de55fcb82653ba089c970834d68c59d03ec809f07c36e86
3
+ size 169924776
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
unsloth_SmolLM2-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff