ThomasTheMaker commited on
Commit
0952dfc
·
verified ·
1 Parent(s): 4261508

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 +43 -0
  2. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  3. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  4. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  5. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  6. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +34 -0
  7. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  8. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +154 -0
  9. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  10. HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  11. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  12. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  13. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  14. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  15. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +34 -0
  16. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  17. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +154 -0
  18. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  19. HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  20. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  21. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  22. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  23. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  24. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +34 -0
  25. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  26. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +154 -0
  27. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  28. HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  29. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  30. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  31. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  32. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  33. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +34 -0
  34. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  35. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +154 -0
  36. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  37. HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  38. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  39. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  40. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  41. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
  42. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/special_tokens_map.json +34 -0
  43. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json +0 -0
  44. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer_config.json +154 -0
  45. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json +0 -0
  46. HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform +3 -0
  47. HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json +31 -0
  48. HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/generation_config.json +8 -0
  49. HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt +0 -0
  50. HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/model.safetensors +3 -0
.gitattributes CHANGED
@@ -34,3 +34,46 @@ saved_model/**/* 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
  HuggingFaceTB_SmolLM2-135M-Instruct_4_layers_2_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform 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
  HuggingFaceTB_SmolLM2-135M-Instruct_4_layers_2_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
37
+ HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
38
+ HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
39
+ HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
40
+ HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
41
+ HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
42
+ HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
43
+ HuggingFaceTB_SmolLM-135M-Instruct_16_layers_1_17_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
44
+ HuggingFaceTB_SmolLM-135M-Instruct_17_layers_1_18_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
45
+ HuggingFaceTB_SmolLM-135M-Instruct_18_layers_3_21_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
46
+ HuggingFaceTB_SmolLM-135M-Instruct_19_layers_2_21_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
47
+ HuggingFaceTB_SmolLM-135M-Instruct_1_layers_2_3_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
48
+ HuggingFaceTB_SmolLM-135M-Instruct_20_layers_1_21_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
49
+ HuggingFaceTB_SmolLM-135M-Instruct_21_layers_1_22_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
50
+ HuggingFaceTB_SmolLM-135M-Instruct_22_layers_1_23_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
51
+ HuggingFaceTB_SmolLM-135M-Instruct_23_layers_2_25_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
52
+ HuggingFaceTB_SmolLM-135M-Instruct_24_layers_1_25_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
53
+ HuggingFaceTB_SmolLM-135M-Instruct_25_layers_1_26_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
54
+ HuggingFaceTB_SmolLM-135M-Instruct_26_layers_1_27_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
55
+ HuggingFaceTB_SmolLM-135M-Instruct_27_layers_1_28_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
56
+ HuggingFaceTB_SmolLM-135M-Instruct_28_layers_1_29_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
57
+ HuggingFaceTB_SmolLM-135M-Instruct_29_layers_1_30_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
58
+ HuggingFaceTB_SmolLM-135M-Instruct_2_layers_4_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
59
+ HuggingFaceTB_SmolLM-135M-Instruct_3_layers_3_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
60
+ HuggingFaceTB_SmolLM-135M-Instruct_4_layers_2_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
61
+ HuggingFaceTB_SmolLM-135M-Instruct_5_layers_4_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
62
+ HuggingFaceTB_SmolLM-135M-Instruct_6_layers_2_8_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
63
+ HuggingFaceTB_SmolLM-135M-Instruct_7_layers_2_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
64
+ HuggingFaceTB_SmolLM-135M-Instruct_8_layers_2_10_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
65
+ HuggingFaceTB_SmolLM-135M-Instruct_9_layers_2_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
66
+ unsloth_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
67
+ unsloth_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
68
+ unsloth_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
69
+ unsloth_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
70
+ unsloth_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
71
+ unsloth_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
72
+ unsloth_SmolLM-135M-Instruct_2_layers_4_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
73
+ unsloth_SmolLM-135M-Instruct_3_layers_3_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
74
+ unsloth_SmolLM-135M-Instruct_4_layers_2_6_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
75
+ unsloth_SmolLM-135M-Instruct_5_layers_4_9_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform filter=lfs diff=lfs merge=lfs -text
76
+ unsloth_SmolLM-135M-Instruct_6_layers_2_8_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
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 20,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_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:d4c7d78e6ee3b03218f117a79348315550730bef57bc251264b6d0f5fc17ebe0
3
+ size 198248456
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_10_layers_1_11_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:d2995ebecf21af8fd33007a2fffb13269c48aaf6977f4a5e35e659142e3e1f6b
3
+ size 2656306
HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 19,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-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 sha256:0241adc67824cbc6eccc15ab5f63d34f94866fe6317fdb74c9a2f8d65b82a89d
3
+ size 191167248
HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-135M-Instruct_11_layers_2_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-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 sha256:28d988d97e50db3f54e0d0922b1fba52774ee6c3d64b88909f03b1ed7093429a
3
+ size 2656306
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 18,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_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:f320fb6870847d28e4b8a70f383bf63c5a95bd62ec82fd00ef22937a9bacbe1c
3
+ size 184086040
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_13_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_12_layers_1_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:c0f64c21639436e3888498f6e232cd597b1bc85f8b3df3b5fec263fc3650f3e2
3
+ size 2656306
HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 17,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-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 sha256:3aef8d37bf8a7f98e15f5348ce806409da0235892c16a3d9ceccebb15e3ec391
3
+ size 177004832
HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-135M-Instruct_13_layers_2_15_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-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:b7668cd067f9a85d7f93b74caa65c09c507a28f11ec192bad96ec061b5fbf397
3
+ size 2656306
HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-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:f3f3c333abf089f8a7eb99fe89c6e68f32515c5a8783871c93054e3f216d7c2c
3
+ size 169923624
HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/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
+ }
HuggingFaceTB_SmolLM-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
 
HuggingFaceTB_SmolLM-135M-Instruct_14_layers_2_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1_transform ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddf527ea22a9f237043b323b98cc3ed03386821e988a9a4a7beb35ed12c0d3b
3
+ size 2656306
HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-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": 0.02,
14
+ "intermediate_size": 1536,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 15,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": null,
25
+ "rope_theta": 10000.0,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.46.3",
29
+ "use_cache": true,
30
+ "vocab_size": 49152
31
+ }
HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_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_new_tokens": 40,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.46.3"
8
+ }
HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_16_Open-Orca_SlimOrca_8000_ReplaceMe_lstsq_1/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
HuggingFaceTB_SmolLM-135M-Instruct_15_layers_1_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:e5fde28b9ce379100ad5b2057eb74fc73657bebf00317596c943e173885a39c9
3
+ size 162842416