Hugging Face's logo

dusty-nv
/
DeepSeek-R1-Distill-Qwen-7B-q4f16_ft-MLC

Model card Files Community
dusty-nv commited on
Commit
b4de9fa
·
verified ·
1 Parent(s): 2374586

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 +1 -0
  2. README.md +19 -0
  3. aarch64-cu126-sm87.so +3 -0
  4. mlc-chat-config.json +76 -0
  5. ndarray-cache.json +0 -0
  6. params_shard_0.bin +3 -0
  7. params_shard_1.bin +3 -0
  8. params_shard_10.bin +3 -0
  9. params_shard_11.bin +3 -0
  10. params_shard_12.bin +3 -0
  11. params_shard_13.bin +3 -0
  12. params_shard_14.bin +3 -0
  13. params_shard_15.bin +3 -0
  14. params_shard_16.bin +3 -0
  15. params_shard_17.bin +3 -0
  16. params_shard_18.bin +3 -0
  17. params_shard_19.bin +3 -0
  18. params_shard_2.bin +3 -0
  19. params_shard_20.bin +3 -0
  20. params_shard_21.bin +3 -0
  21. params_shard_22.bin +3 -0
  22. params_shard_23.bin +3 -0
  23. params_shard_24.bin +3 -0
  24. params_shard_25.bin +3 -0
  25. params_shard_26.bin +3 -0
  26. params_shard_27.bin +3 -0
  27. params_shard_28.bin +3 -0
  28. params_shard_29.bin +3 -0
  29. params_shard_3.bin +3 -0
  30. params_shard_30.bin +3 -0
  31. params_shard_31.bin +3 -0
  32. params_shard_32.bin +3 -0
  33. params_shard_33.bin +3 -0
  34. params_shard_34.bin +3 -0
  35. params_shard_35.bin +3 -0
  36. params_shard_36.bin +3 -0
  37. params_shard_37.bin +3 -0
  38. params_shard_38.bin +3 -0
  39. params_shard_39.bin +3 -0
  40. params_shard_4.bin +3 -0
  41. params_shard_40.bin +3 -0
  42. params_shard_41.bin +3 -0
  43. params_shard_42.bin +3 -0
  44. params_shard_43.bin +3 -0
  45. params_shard_44.bin +3 -0
  46. params_shard_45.bin +3 -0
  47. params_shard_46.bin +3 -0
  48. params_shard_47.bin +3 -0
  49. params_shard_48.bin +3 -0
  50. params_shard_49.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ aarch64-cu126-sm87.so filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # DeepSeek-R1-Distill-Qwen-7B-q4f16_ft-MLC
2
+
3
+ | | Model Configuration |
4
+ |---------------------|:-----------------------------------------------------------------------------------------------------------:|
5
+ | Source Model | [`deepseek-ai/DeepSeek-R1-Distill-Qwen-7B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) |
6
+ | Inference API | `MLC_LLM` |
7
+ | Quantization | `q4f16_ft` |
8
+ | Model Type | `qwen2` |
9
+ | Vocab Size | `152064` |
10
+ | Context Window Size | `131072` |
11
+ | Prefill Chunk Size | `8192` |
12
+ | Temperature | `0.6` |
13
+ | Repetition Penalty | `1.0` |
14
+ | top_p | `0.95` |
15
+ | pad_token_id | `0` |
16
+ | bos_token_id | `151646` |
17
+ | eos_token_id | `151643` |
18
+
19
+ See [`jetson-ai-lab.com/models.html`](https://jetson-ai-lab.com/models.html) for benchmarks, examples, and containers to deploy local serving and inference for these quantized models.
aarch64-cu126-sm87.so ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8224425f6d7052fcb809a0208dbdcf6c7d4e5df955404d4f378bdb0a30f1dbe0
3
+ size 9855032
mlc-chat-config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "qwen2",
4
+ "quantization": "q4f16_ft",
5
+ "model_config": {
6
+ "hidden_act": "silu",
7
+ "hidden_size": 3584,
8
+ "intermediate_size": 18944,
9
+ "num_attention_heads": 28,
10
+ "num_hidden_layers": 28,
11
+ "num_key_value_heads": 4,
12
+ "rms_norm_eps": 1e-06,
13
+ "rope_theta": 10000,
14
+ "vocab_size": 152064,
15
+ "tie_word_embeddings": false,
16
+ "context_window_size": 131072,
17
+ "prefill_chunk_size": 8192,
18
+ "tensor_parallel_shards": 1,
19
+ "head_dim": 128,
20
+ "dtype": "float32",
21
+ "max_batch_size": 1
22
+ },
23
+ "vocab_size": 152064,
24
+ "context_window_size": 131072,
25
+ "sliding_window_size": -1,
26
+ "prefill_chunk_size": 8192,
27
+ "attention_sink_size": -1,
28
+ "tensor_parallel_shards": 1,
29
+ "pipeline_parallel_stages": 1,
30
+ "temperature": 0.6,
31
+ "presence_penalty": 0.0,
32
+ "frequency_penalty": 0.0,
33
+ "repetition_penalty": 1.0,
34
+ "top_p": 0.95,
35
+ "tokenizer_files": [
36
+ "tokenizer.json",
37
+ "tokenizer_config.json"
38
+ ],
39
+ "tokenizer_info": {
40
+ "token_postproc_method": "byte_level",
41
+ "prepend_space_in_encode": false,
42
+ "strip_space_in_decode": false
43
+ },
44
+ "conv_template": {
45
+ "name": "deepseek_r1_qwen",
46
+ "system_template": "<\uff5cbegin\u2581of\u2581sentence\uff5c>{system_message}",
47
+ "system_message": "You are a helpful assistant.",
48
+ "system_prefix_token_ids": null,
49
+ "add_role_after_system_message": true,
50
+ "roles": {
51
+ "user": "<\uff5cUser\uff5c>",
52
+ "assistant": "<\uff5cAssistant\uff5c>"
53
+ },
54
+ "role_templates": {
55
+ "user": "{user_message}",
56
+ "assistant": "{assistant_message}",
57
+ "tool": "{tool_message}"
58
+ },
59
+ "messages": [],
60
+ "seps": [
61
+ "",
62
+ "<\uff5cend\u2581of\u2581sentence\uff5c>"
63
+ ],
64
+ "role_content_sep": "",
65
+ "role_empty_sep": "",
66
+ "stop_str": [],
67
+ "stop_token_ids": [
68
+ 151643
69
+ ],
70
+ "function_string": "",
71
+ "use_function_calling": false
72
+ },
73
+ "pad_token_id": 0,
74
+ "bos_token_id": 151646,
75
+ "eos_token_id": 151643
76
+ }
ndarray-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e6d533a212ee685dbf8f728e828fe8e8358dd42c256031ff6eb2039f7b22f0
3
+ size 272498688
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253d7a9c6c15be3b3f5c2089383ff41b63415e4208c2bace4497460488d1b250
3
+ size 34062336
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00203787495e305125a8141bba2b8f5d3507672a65b7dfb157d647758182c46e
3
+ size 33947648
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:253da6638b33e6c409d461bc6d15c49ada3fbd76986fb72fe37e03670db413ce
3
+ size 29605888
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3d489e9de2e5731d407ca914947fb1dad627a427a6d3710f53bf7fe412e236
3
+ size 67895296
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1373bd72200ac3f1991250ede23b16c2ca52c330893b09702b6e146944468d73
3
+ size 33947648
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fa214eff6449ebc540a00dcdf24e0e51924e2c75c0d1b60c507ad26022a2557
3
+ size 67895296
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e672fc25c543f9fbfde3ee1984abc749934465241bf22173f9c7ef14ddd9c28
3
+ size 33947648
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3394dfe3f15269d6c9b3c29c8a5c683336d20abfd3bc669ecdff8f3d0da6e35
3
+ size 29605888
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7483fb373dfd0a2532538b02c217233e94b79acda6852b7c31b599261bedb9
3
+ size 67895296
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23dae5a8c806177d85166518ebe4b5106d10158b63ed9c38435eaa13c43f787a
3
+ size 33947648
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bd1629b3a2a986805448a17abf7f70b620ce95d19739d13debeb482ceed901
3
+ size 67895296
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3cfb588d71ed7575162e69337ebf31314d3d7c398df717173c9c4b4c3e0adf
3
+ size 67895296
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2632c5b030f4c2007dbc3256a5b4068c23cf7a55b3f6bc3c9e99bf6f61e747
3
+ size 33947648
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f230ce07a720d44cc61cb2efcadace5f9137fc08ed66335007cdbd38bff2e68
3
+ size 29605888
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9892b0191e1978fe3bc8027778bcacb35d68cde513adc65d842619017edcf833
3
+ size 67895296
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ccc1c464e01b460e001309615dd3a0fc47d9e3d59de9d7cbeaf31a9a559229
3
+ size 33947648
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b01aed0cd06fdb2554d6e7571eba59cd23608ce91ceb23b35f18276795b5e0
3
+ size 67895296
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb428eb98fbff3cb5076514138c4de1f7c43b021ab12356fe1a9d5459d8312c4
3
+ size 33947648
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01ceefc736076ff99d28bf464909286fa476dc1fb1de08c4b163c4f44bbc0107
3
+ size 29605888
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77536c6a01693afe831b1ef7793000e6abb4318c4d66e383658e11953e97c739
3
+ size 67895296
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534c932224454f039d8614e693f5c588daf62971897b75709599283a0ad33006
3
+ size 33947648
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04cc6b352d63c0641f80460aa2fb61f36a8e921aa956d7290f678ba5191798f
3
+ size 67895296
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0d09d215f18d434d1e0818e940b3f45673f4bcf2bb584aabb34236455d3aba
3
+ size 33947648
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4830ca7f8711426e5a7ab6680c3029a8df3bc251c4a127107d182a8a45840c94
3
+ size 33947648
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9d9e411b515ae875599e83fcc08522c5725d07d2da8264b5b7e629a9bb97eb
3
+ size 29605888
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98a5f4d07b0e0fb2aa24eba85a2b2b8b4638403a69eee2f6d322cdbec2783aa9
3
+ size 67895296
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7be78316756f5c862a913f51d85d229698c81672fac2b40c3ebf6b3661744c
3
+ size 33947648
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6975eb4b0602364c027c73acc62703d06e9a4d8e374181004647a69dcce6fae
3
+ size 67895296
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47262ba207837e9f322ff6f274a75810a441890d6f0e88cd22fa1522b14553f8
3
+ size 33947648
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f76b5e2e800ee1999db77f829c72624a2292eefdfe947bd999c85e335106e105
3
+ size 29605888
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22891212e90b0ec0d0f1b54a7dbddbfa7e810eb0d5429ba4b6eabe1598413e72
3
+ size 67895296
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4171ec8116faa17ecd92216b047e517d4ea480ee1e03f17f7959fa9c55d53743
3
+ size 33947648
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043f4277b5653c8f44956659c028ea75a7d1ed3274f86822e4b013c008dd0618
3
+ size 67895296
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a657ed37c35488f374b3696ca8a897e9dfdcf758778844606596384e788228bb
3
+ size 67895296
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b332901b4c0d271d669e4f2025fbdbacd12430540c1ecf912c260f0580d0d2e
3
+ size 33947648
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c303212d106de6585ebf212a67225973e7b6207689c408f507977191d4c84ec8
3
+ size 29605888
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359e15d4b66a092f6e49c7ddd50e4d7a84f6762b2cfeb435b573f88976934822
3
+ size 67895296
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c122ec218421ce136ff414aa821ab18dc718541a358f10b550b4c042c44532fc
3
+ size 33947648
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c923776dd7cfd58a3124709b15dbd2e1ee466214a8d109172afac24721e920
3
+ size 67895296
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34602ae10795af298ca04a8e3e384a2d9978460c4e98a21d1a8fadf64bb20a7
3
+ size 33947648
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3edb4c4c6743957bb06bce5cf4ab6e7f73973ac2c8b5fe27a7fe88a5575e36b3
3
+ size 29605888
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4077a90fdbd11ec4fec317ca2854307c2f8b196b357aa5eaef0382ae3b5ef4f2
3
+ size 67895296
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62c2b3ee3ff37efb894ef14130f06bc44907676754ff86595e1b553b4105df1
3
+ size 33947648
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd845cc9ceee83dbb9c1de30933ff92092447c3aaade4b5cf3c3a6858f6150dc
3
+ size 67895296