Hugging Face's logo

ThomasTheMaker
/
Smollm2-360M-Instruct-RKLLM-1.2.1B

llama
Model card Files
xet
 Community
ThomasTheMaker commited on
Commit
4e551e6
·
verified ·
1 Parent(s): c135433

Upload folder using huggingface_hub

Browse files
Files changed (47) hide show
  1. .gitattributes +13 -0
  2. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/0ad5ecc2035b7031b88afb544ee95e2d49baa484.lock +0 -0
  3. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/44719d2e365acac0637fd25a3acf46494ca45940.lock +0 -0
  4. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/4f2ae86545bb5c1d4fcc55644deef86be50a7dee.lock +0 -0
  5. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/69503b13f727ba3812b6803e97442a6de05ef5eb.lock +0 -0
  6. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/8c7b22013909450429303ed10be4398bd63f5457.lock +0 -0
  7. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/da6c4d71a43aa7e6f785bdbb28ea5025438a73fa.lock +0 -0
  8. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e.lock +0 -0
  9. .locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/f922b1797f0c88e71addc8393787831f2477a4bd.lock +0 -0
  10. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm +3 -0
  11. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm +3 -0
  12. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm +3 -0
  13. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm +3 -0
  14. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm +3 -0
  15. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm +3 -0
  16. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm +3 -0
  17. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm +3 -0
  18. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm +3 -0
  19. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm +3 -0
  20. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm +3 -0
  21. HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm +3 -0
  22. config.json +38 -0
  23. conversion_log.txt +145 -0
  24. generation_config.json +7 -0
  25. merges.txt +0 -0
  26. models--HuggingFaceTB--SmolLM2-360M-Instruct/.no_exist/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/added_tokens.json +0 -0
  27. models--HuggingFaceTB--SmolLM2-360M-Instruct/.no_exist/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/chat_template.jinja +0 -0
  28. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/0ad5ecc2035b7031b88afb544ee95e2d49baa484 +0 -0
  29. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/44719d2e365acac0637fd25a3acf46494ca45940 +34 -0
  30. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/4f2ae86545bb5c1d4fcc55644deef86be50a7dee +37 -0
  31. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/69503b13f727ba3812b6803e97442a6de05ef5eb +0 -0
  32. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/8c7b22013909450429303ed10be4398bd63f5457 +154 -0
  33. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/da6c4d71a43aa7e6f785bdbb28ea5025438a73fa +7 -0
  34. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e +3 -0
  35. models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/f922b1797f0c88e71addc8393787831f2477a4bd +0 -0
  36. models--HuggingFaceTB--SmolLM2-360M-Instruct/refs/main +1 -0
  37. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/config.json +37 -0
  38. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/generation_config.json +7 -0
  39. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/merges.txt +0 -0
  40. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/special_tokens_map.json +34 -0
  41. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/tokenizer.json +0 -0
  42. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/tokenizer_config.json +154 -0
  43. models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/vocab.json +0 -0
  44. special_tokens_map.json +34 -0
  45. tokenizer.json +0 -0
  46. tokenizer_config.json +155 -0
  47. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
37
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
38
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
39
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
40
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
41
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
42
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
43
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
44
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
45
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
46
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
47
+ HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm filter=lfs diff=lfs merge=lfs -text
48
+ models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e filter=lfs diff=lfs merge=lfs -text
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/0ad5ecc2035b7031b88afb544ee95e2d49baa484.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/44719d2e365acac0637fd25a3acf46494ca45940.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/4f2ae86545bb5c1d4fcc55644deef86be50a7dee.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/69503b13f727ba3812b6803e97442a6de05ef5eb.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/8c7b22013909450429303ed10be4398bd63f5457.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/da6c4d71a43aa7e6f785bdbb28ea5025438a73fa.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e.lock ADDED
File without changes
.locks/models--HuggingFaceTB--SmolLM2-360M-Instruct/f922b1797f0c88e71addc8393787831f2477a4bd.lock ADDED
File without changes
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb35c3d89603bcbfcc499334da27917a9634da9f34e651d40ceccdcbf0ab1297
3
+ size 472976310
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5ae0f45139f4048bbb85ce27783d0f98ae926ea84317e20dcf08b0ba3ebcd9
3
+ size 466040230
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef641b116d9b0190bdc9f228270a46e794d99e0895943979f3093bbd8f431546
3
+ size 485217998
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d7a1a8f84fc750ee00b4d13f82a0cb8f674188e2ff296e5dd6616a683635fc
3
+ size 471345798
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec42f265fc3139627b3b128ce8da014e7b5efc8a83cef82e1f4202a7d0e9bb7d
3
+ size 497433726
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c329bbd0aaa53214a6b1d6cb290eeec2527b64ed5cad6e29bc16f3b7e36e83
3
+ size 476625430
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb35c3d89603bcbfcc499334da27917a9634da9f34e651d40ceccdcbf0ab1297
3
+ size 472976310
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb5ae0f45139f4048bbb85ce27783d0f98ae926ea84317e20dcf08b0ba3ebcd9
3
+ size 466040230
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef641b116d9b0190bdc9f228270a46e794d99e0895943979f3093bbd8f431546
3
+ size 485217998
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d7a1a8f84fc750ee00b4d13f82a0cb8f674188e2ff296e5dd6616a683635fc
3
+ size 471345798
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec42f265fc3139627b3b128ce8da014e7b5efc8a83cef82e1f4202a7d0e9bb7d
3
+ size 497433726
HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54c329bbd0aaa53214a6b1d6cb290eeec2527b64ed5cad6e29bc16f3b7e36e83
3
+ size 476625430
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2560,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 15,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 5,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "float32",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "fp16": "float16",
32
+ "q4f16": "float16"
33
+ }
34
+ },
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": true,
37
+ "vocab_size": 49152
38
+ }
conversion_log.txt ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-08-04 08:59:29,418 - INFO - Starting conversion for model: HuggingFaceTB/SmolLM2-360M-Instruct
2
+ 2025-08-04 08:59:29,418 - INFO - Model folder: model/HuggingFaceTB_SmolLM2-360M-Instruct
3
+ 2025-08-04 08:59:29,419 - INFO - Log file: model/HuggingFaceTB_SmolLM2-360M-Instruct/conversion_log.txt
4
+ 2025-08-04 08:59:29,419 - INFO - Model compatibility rules: {'supported_quantized_dtypes': ['w8a8'], 'supported_hybrid_rates': [0], 'notes': 'Only basic w8a8 quantization works, no grouped quantization or hybrid quantization'}
5
+ 2025-08-04 08:59:29,419 - INFO - Generated 96 parameter combinations
6
+ 2025-08-04 08:59:29,419 - INFO - Filtered to 12 compatible combinations
7
+ 2025-08-04 08:59:29,419 - INFO - Processing combination 1/12: w8a8-opt0-hybrid0-npu1-ctx4032-rk3588
8
+ 2025-08-04 08:59:29,632 - INFO - rkllm-toolkit version: 1.2.1b1
9
+ 2025-08-04 09:00:22,598 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
10
+ 2025-08-04 09:00:23,284 - INFO - Setting token_id of bos to 1
11
+ 2025-08-04 09:00:23,285 - INFO - Setting token_id of eos to 2
12
+ 2025-08-04 09:00:23,285 - INFO - Setting token_id of unk to 0
13
+ 2025-08-04 09:00:23,285 - INFO - Setting token_id of pad to 2
14
+ 2025-08-04 09:00:26,499 - INFO - Setting max_context_limit to 4032
15
+ 2025-08-04 09:00:28,225 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm!
16
+ 2025-08-04 09:00:28,225 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm (Time: 58.81s)
17
+ 2025-08-04 09:00:28,226 - INFO - Processing combination 2/12: w8a8-opt0-hybrid0-npu2-ctx4032-rk3588
18
+ 2025-08-04 09:00:28,226 - INFO - rkllm-toolkit version: 1.2.1b1
19
+ 2025-08-04 09:01:19,391 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
20
+ 2025-08-04 09:01:20,077 - INFO - Setting token_id of bos to 1
21
+ 2025-08-04 09:01:20,077 - INFO - Setting token_id of eos to 2
22
+ 2025-08-04 09:01:20,078 - INFO - Setting token_id of unk to 0
23
+ 2025-08-04 09:01:20,078 - INFO - Setting token_id of pad to 2
24
+ 2025-08-04 09:01:23,067 - INFO - Setting max_context_limit to 4032
25
+ 2025-08-04 09:01:26,023 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm!
26
+ 2025-08-04 09:01:26,024 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm (Time: 57.80s)
27
+ 2025-08-04 09:01:26,024 - INFO - Processing combination 3/12: w8a8-opt0-hybrid0-npu3-ctx4032-rk3588
28
+ 2025-08-04 09:01:26,024 - INFO - rkllm-toolkit version: 1.2.1b1
29
+ 2025-08-04 09:02:17,411 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
30
+ 2025-08-04 09:02:18,093 - INFO - Setting token_id of bos to 1
31
+ 2025-08-04 09:02:18,094 - INFO - Setting token_id of eos to 2
32
+ 2025-08-04 09:02:18,094 - INFO - Setting token_id of unk to 0
33
+ 2025-08-04 09:02:18,094 - INFO - Setting token_id of pad to 2
34
+ 2025-08-04 09:02:20,936 - INFO - Setting max_context_limit to 4032
35
+ 2025-08-04 09:02:25,102 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm!
36
+ 2025-08-04 09:02:25,102 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm (Time: 59.08s)
37
+ 2025-08-04 09:02:25,102 - INFO - Processing combination 4/12: w8a8-opt0-hybrid0-npu1-ctx16384-rk3588
38
+ 2025-08-04 09:02:25,102 - INFO - rkllm-toolkit version: 1.2.1b1
39
+ 2025-08-04 09:03:16,418 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
40
+ 2025-08-04 09:03:17,109 - INFO - Setting token_id of bos to 1
41
+ 2025-08-04 09:03:17,109 - INFO - Setting token_id of eos to 2
42
+ 2025-08-04 09:03:17,110 - INFO - Setting token_id of unk to 0
43
+ 2025-08-04 09:03:17,110 - INFO - Setting token_id of pad to 2
44
+ 2025-08-04 09:03:19,862 - INFO - Setting max_context_limit to 16384
45
+ 2025-08-04 09:03:24,225 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm!
46
+ 2025-08-04 09:03:24,226 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm (Time: 59.12s)
47
+ 2025-08-04 09:03:24,226 - INFO - Processing combination 5/12: w8a8-opt0-hybrid0-npu2-ctx16384-rk3588
48
+ 2025-08-04 09:03:24,226 - INFO - rkllm-toolkit version: 1.2.1b1
49
+ 2025-08-04 09:04:15,520 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
50
+ 2025-08-04 09:04:16,205 - INFO - Setting token_id of bos to 1
51
+ 2025-08-04 09:04:16,205 - INFO - Setting token_id of eos to 2
52
+ 2025-08-04 09:04:16,205 - INFO - Setting token_id of unk to 0
53
+ 2025-08-04 09:04:16,205 - INFO - Setting token_id of pad to 2
54
+ 2025-08-04 09:04:19,111 - INFO - Setting max_context_limit to 16384
55
+ 2025-08-04 09:04:27,510 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm!
56
+ 2025-08-04 09:04:27,510 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm (Time: 63.28s)
57
+ 2025-08-04 09:04:27,510 - INFO - Processing combination 6/12: w8a8-opt0-hybrid0-npu3-ctx16384-rk3588
58
+ 2025-08-04 09:04:27,510 - INFO - rkllm-toolkit version: 1.2.1b1
59
+ 2025-08-04 09:05:18,689 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
60
+ 2025-08-04 09:05:19,373 - INFO - Setting token_id of bos to 1
61
+ 2025-08-04 09:05:19,373 - INFO - Setting token_id of eos to 2
62
+ 2025-08-04 09:05:19,373 - INFO - Setting token_id of unk to 0
63
+ 2025-08-04 09:05:19,373 - INFO - Setting token_id of pad to 2
64
+ 2025-08-04 09:05:22,298 - INFO - Setting max_context_limit to 16384
65
+ 2025-08-04 09:05:34,862 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm!
66
+ 2025-08-04 09:05:34,863 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm (Time: 67.35s)
67
+ 2025-08-04 09:05:34,863 - INFO - Processing combination 7/12: w8a8-opt1-hybrid0-npu1-ctx4032-rk3588
68
+ 2025-08-04 09:05:34,863 - INFO - rkllm-toolkit version: 1.2.1b1
69
+ 2025-08-04 09:06:26,041 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
70
+ 2025-08-04 09:06:26,723 - INFO - Setting token_id of bos to 1
71
+ 2025-08-04 09:06:26,723 - INFO - Setting token_id of eos to 2
72
+ 2025-08-04 09:06:26,723 - INFO - Setting token_id of unk to 0
73
+ 2025-08-04 09:06:26,723 - INFO - Setting token_id of pad to 2
74
+ 2025-08-04 09:06:29,719 - INFO - Setting max_context_limit to 4032
75
+ 2025-08-04 09:06:31,396 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm!
76
+ 2025-08-04 09:06:31,396 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm (Time: 56.53s)
77
+ 2025-08-04 09:06:31,396 - INFO - Processing combination 8/12: w8a8-opt1-hybrid0-npu2-ctx4032-rk3588
78
+ 2025-08-04 09:06:31,396 - INFO - rkllm-toolkit version: 1.2.1b1
79
+ 2025-08-04 09:07:22,751 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
80
+ 2025-08-04 09:07:23,428 - INFO - Setting token_id of bos to 1
81
+ 2025-08-04 09:07:23,428 - INFO - Setting token_id of eos to 2
82
+ 2025-08-04 09:07:23,428 - INFO - Setting token_id of unk to 0
83
+ 2025-08-04 09:07:23,428 - INFO - Setting token_id of pad to 2
84
+ 2025-08-04 09:07:26,177 - INFO - Setting max_context_limit to 4032
85
+ 2025-08-04 09:07:29,065 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm!
86
+ 2025-08-04 09:07:29,066 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm (Time: 57.67s)
87
+ 2025-08-04 09:07:29,066 - INFO - Processing combination 9/12: w8a8-opt1-hybrid0-npu3-ctx4032-rk3588
88
+ 2025-08-04 09:07:29,066 - INFO - rkllm-toolkit version: 1.2.1b1
89
+ 2025-08-04 09:08:20,450 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
90
+ 2025-08-04 09:08:21,138 - INFO - Setting token_id of bos to 1
91
+ 2025-08-04 09:08:21,139 - INFO - Setting token_id of eos to 2
92
+ 2025-08-04 09:08:21,139 - INFO - Setting token_id of unk to 0
93
+ 2025-08-04 09:08:21,139 - INFO - Setting token_id of pad to 2
94
+ 2025-08-04 09:08:23,932 - INFO - Setting max_context_limit to 4032
95
+ 2025-08-04 09:08:28,040 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm!
96
+ 2025-08-04 09:08:28,040 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm (Time: 58.97s)
97
+ 2025-08-04 09:08:28,040 - INFO - Processing combination 10/12: w8a8-opt1-hybrid0-npu1-ctx16384-rk3588
98
+ 2025-08-04 09:08:28,040 - INFO - rkllm-toolkit version: 1.2.1b1
99
+ 2025-08-04 09:09:19,521 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
100
+ 2025-08-04 09:09:20,198 - INFO - Setting token_id of bos to 1
101
+ 2025-08-04 09:09:20,198 - INFO - Setting token_id of eos to 2
102
+ 2025-08-04 09:09:20,198 - INFO - Setting token_id of unk to 0
103
+ 2025-08-04 09:09:20,198 - INFO - Setting token_id of pad to 2
104
+ 2025-08-04 09:09:22,937 - INFO - Setting max_context_limit to 16384
105
+ 2025-08-04 09:09:27,265 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm!
106
+ 2025-08-04 09:09:27,265 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm (Time: 59.22s)
107
+ 2025-08-04 09:09:27,265 - INFO - Processing combination 11/12: w8a8-opt1-hybrid0-npu2-ctx16384-rk3588
108
+ 2025-08-04 09:09:27,266 - INFO - rkllm-toolkit version: 1.2.1b1
109
+ 2025-08-04 09:10:18,692 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
110
+ 2025-08-04 09:10:19,384 - INFO - Setting token_id of bos to 1
111
+ 2025-08-04 09:10:19,384 - INFO - Setting token_id of eos to 2
112
+ 2025-08-04 09:10:19,384 - INFO - Setting token_id of unk to 0
113
+ 2025-08-04 09:10:19,384 - INFO - Setting token_id of pad to 2
114
+ 2025-08-04 09:10:22,285 - INFO - Setting max_context_limit to 16384
115
+ 2025-08-04 09:10:30,771 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm!
116
+ 2025-08-04 09:10:30,771 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm (Time: 63.51s)
117
+ 2025-08-04 09:10:30,771 - INFO - Processing combination 12/12: w8a8-opt1-hybrid0-npu3-ctx16384-rk3588
118
+ 2025-08-04 09:10:30,771 - INFO - rkllm-toolkit version: 1.2.1b1
119
+ 2025-08-04 09:11:22,003 - INFO - Setting chat_template to "<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n<|im_start|>user\n[content]<|im_end|>\n<|im_start|>assistant\n"
120
+ 2025-08-04 09:11:22,673 - INFO - Setting token_id of bos to 1
121
+ 2025-08-04 09:11:22,673 - INFO - Setting token_id of eos to 2
122
+ 2025-08-04 09:11:22,673 - INFO - Setting token_id of unk to 0
123
+ 2025-08-04 09:11:22,673 - INFO - Setting token_id of pad to 2
124
+ 2025-08-04 09:11:25,547 - INFO - Setting max_context_limit to 16384
125
+ 2025-08-04 09:11:38,079 - INFO - Model has been saved to model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm!
126
+ 2025-08-04 09:11:38,079 - INFO - Successfully exported: model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm (Time: 67.31s)
127
+ 2025-08-04 09:11:38,080 - INFO - Conversion complete!
128
+ 2025-08-04 09:11:38,081 - INFO - Total time: 728.66s
129
+ 2025-08-04 09:11:38,081 - INFO - Successful conversions: 12
130
+ 2025-08-04 09:11:38,081 - INFO - Failed conversions: 0
131
+ 2025-08-04 09:11:38,081 - INFO - Success rate: 100.0%
132
+ 2025-08-04 09:11:38,081 - INFO - Total combinations processed: 12
133
+ 2025-08-04 09:11:38,081 - INFO - Successfully generated models:
134
+ 2025-08-04 09:11:38,081 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx4032-rk3588.rkllm (444.5 MB)
135
+ 2025-08-04 09:11:38,081 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx4032-rk3588.rkllm (449.5 MB)
136
+ 2025-08-04 09:11:38,081 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx4032-rk3588.rkllm (454.5 MB)
137
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu1-ctx16384-rk3588.rkllm (451.1 MB)
138
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu2-ctx16384-rk3588.rkllm (462.7 MB)
139
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt0-hybrid0-npu3-ctx16384-rk3588.rkllm (474.4 MB)
140
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx4032-rk3588.rkllm (444.5 MB)
141
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx4032-rk3588.rkllm (449.5 MB)
142
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx4032-rk3588.rkllm (454.5 MB)
143
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu1-ctx16384-rk3588.rkllm (451.1 MB)
144
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu2-ctx16384-rk3588.rkllm (462.7 MB)
145
+ 2025-08-04 09:11:38,082 - INFO - - model/HuggingFaceTB_SmolLM2-360M-Instruct/HuggingFaceTB_SmolLM2-360M-Instruct-w8a8-opt1-hybrid0-npu3-ctx16384-rk3588.rkllm (474.4 MB)
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.51.3"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/.no_exist/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/added_tokens.json ADDED
File without changes
models--HuggingFaceTB--SmolLM2-360M-Instruct/.no_exist/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/chat_template.jinja ADDED
File without changes
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/0ad5ecc2035b7031b88afb544ee95e2d49baa484 ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/44719d2e365acac0637fd25a3acf46494ca45940 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
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/4f2ae86545bb5c1d4fcc55644deef86be50a7dee ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 960,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2560,
13
+ "is_llama_config": true,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 15,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 5,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_interleaved": false,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.42.3",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "q4f16": "float16",
32
+ "fp16": "float16"
33
+ }
34
+ },
35
+ "use_cache": true,
36
+ "vocab_size": 49152
37
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/69503b13f727ba3812b6803e97442a6de05ef5eb ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/8c7b22013909450429303ed10be4398bd63f5457 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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "model_max_length": 8192,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/da6c4d71a43aa7e6f785bdbb28ea5025438a73fa ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.42.3"
7
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bffe7435d7ddc10fd3b9a9efd429dafbacb1cb17015fb5562664e7532bf86e
3
+ size 723674912
models--HuggingFaceTB--SmolLM2-360M-Instruct/blobs/f922b1797f0c88e71addc8393787831f2477a4bd ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/refs/main ADDED
@@ -0,0 +1 @@
 
 
1
+ c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 960,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2560,
13
+ "is_llama_config": true,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 15,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 5,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_interleaved": false,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.42.3",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "q4f16": "float16",
32
+ "fp16": "float16"
33
+ }
34
+ },
35
+ "use_cache": true,
36
+ "vocab_size": 49152
37
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.42.3"
7
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/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
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "model_max_length": 8192,
150
+ "pad_token": "<|im_end|>",
151
+ "tokenizer_class": "GPT2Tokenizer",
152
+ "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
154
+ }
models--HuggingFaceTB--SmolLM2-360M-Instruct/snapshots/c38281e01d0c0b0c36eac2f5bcb5b51fa2e803fc/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "extra_special_tokens": {},
150
+ "model_max_length": 8192,
151
+ "pad_token": "<|im_end|>",
152
+ "tokenizer_class": "GPT2Tokenizer",
153
+ "unk_token": "<|endoftext|>",
154
+ "vocab_size": 49152
155
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff