Hugging Face's logo

dusty-nv
/
DeepSeek-R1-Distill-Llama-8B-q4f16_ft-MLC

Model card Files Community
dusty-nv commited on
Commit
36ea62d
·
verified ·
1 Parent(s): 8cf0f18

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 +2 -0
  2. README.md +17 -0
  3. aarch64-cu126-sm87.so +3 -0
  4. mlc-chat-config.json +83 -0
  5. model.so +3 -0
  6. ndarray-cache.json +0 -0
  7. params_shard_0.bin +3 -0
  8. params_shard_1.bin +3 -0
  9. params_shard_10.bin +3 -0
  10. params_shard_11.bin +3 -0
  11. params_shard_12.bin +3 -0
  12. params_shard_13.bin +3 -0
  13. params_shard_14.bin +3 -0
  14. params_shard_15.bin +3 -0
  15. params_shard_16.bin +3 -0
  16. params_shard_17.bin +3 -0
  17. params_shard_18.bin +3 -0
  18. params_shard_19.bin +3 -0
  19. params_shard_2.bin +3 -0
  20. params_shard_20.bin +3 -0
  21. params_shard_21.bin +3 -0
  22. params_shard_22.bin +3 -0
  23. params_shard_23.bin +3 -0
  24. params_shard_24.bin +3 -0
  25. params_shard_25.bin +3 -0
  26. params_shard_26.bin +3 -0
  27. params_shard_27.bin +3 -0
  28. params_shard_28.bin +3 -0
  29. params_shard_29.bin +3 -0
  30. params_shard_3.bin +3 -0
  31. params_shard_30.bin +3 -0
  32. params_shard_31.bin +3 -0
  33. params_shard_32.bin +3 -0
  34. params_shard_33.bin +3 -0
  35. params_shard_34.bin +3 -0
  36. params_shard_35.bin +3 -0
  37. params_shard_36.bin +3 -0
  38. params_shard_37.bin +3 -0
  39. params_shard_38.bin +3 -0
  40. params_shard_39.bin +3 -0
  41. params_shard_4.bin +3 -0
  42. params_shard_40.bin +3 -0
  43. params_shard_41.bin +3 -0
  44. params_shard_42.bin +3 -0
  45. params_shard_43.bin +3 -0
  46. params_shard_44.bin +3 -0
  47. params_shard_45.bin +3 -0
  48. params_shard_46.bin +3 -0
  49. params_shard_47.bin +3 -0
  50. params_shard_48.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ model.so filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # DeepSeek-R1-Distill-Llama-8B-q4f16_ft-MLC
2
+
3
+ |-----------------------|------------|
4
+ | `API` | `MLC LLM` |
5
+ | `quantization` | `q4f16_ft` |
6
+ | `model_type` | `llama` |
7
+ | `vocab_size` | `128256` |
8
+ | `context_window_size` | `131072` |
9
+ | `prefill_chunk_size` | `8192` |
10
+ | `temperature` | `0.6` |
11
+ | `repetition_penalty` | `1.0` |
12
+ | `top_p` | `0.95` |
13
+ | `pad_token_id` | `0` |
14
+ | `bos_token_id` | `128000` |
15
+ | `eos_token_id` | `128001` |
16
+
17
+ 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:ce6d206bc6b6b382a004bd83851b422750aeb0a9bff4e7324fc8391281a1c6bc
3
+ size 12198728
mlc-chat-config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q4f16_ft",
5
+ "model_config": {
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 14336,
8
+ "num_attention_heads": 32,
9
+ "num_hidden_layers": 32,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 128256,
12
+ "tie_word_embeddings": false,
13
+ "position_embedding_base": 500000.0,
14
+ "rope_scaling": {
15
+ "factor": 8.0,
16
+ "low_freq_factor": 1.0,
17
+ "high_freq_factor": 4.0,
18
+ "original_max_position_embeddings": 8192,
19
+ "rope_type": "llama3"
20
+ },
21
+ "context_window_size": 131072,
22
+ "prefill_chunk_size": 8192,
23
+ "num_key_value_heads": 8,
24
+ "head_dim": 128,
25
+ "tensor_parallel_shards": 1,
26
+ "pipeline_parallel_stages": 1,
27
+ "max_batch_size": 1,
28
+ "disaggregation": false
29
+ },
30
+ "vocab_size": 128256,
31
+ "context_window_size": 131072,
32
+ "sliding_window_size": -1,
33
+ "prefill_chunk_size": 8192,
34
+ "attention_sink_size": -1,
35
+ "tensor_parallel_shards": 1,
36
+ "pipeline_parallel_stages": 1,
37
+ "temperature": 0.6,
38
+ "presence_penalty": 0.0,
39
+ "frequency_penalty": 0.0,
40
+ "repetition_penalty": 1.0,
41
+ "top_p": 0.95,
42
+ "tokenizer_files": [
43
+ "tokenizer.json",
44
+ "tokenizer_config.json"
45
+ ],
46
+ "tokenizer_info": {
47
+ "token_postproc_method": "byte_level",
48
+ "prepend_space_in_encode": false,
49
+ "strip_space_in_decode": false
50
+ },
51
+ "conv_template": {
52
+ "name": "deepseek_r1_llama",
53
+ "system_template": "<\uff5cbegin\u2581of\u2581sentence\uff5c>{system_message}",
54
+ "system_message": "You are a helpful assistant.",
55
+ "system_prefix_token_ids": null,
56
+ "add_role_after_system_message": true,
57
+ "roles": {
58
+ "user": "<\uff5cUser\uff5c>",
59
+ "assistant": "<\uff5cAssistant\uff5c>"
60
+ },
61
+ "role_templates": {
62
+ "user": "{user_message}",
63
+ "assistant": "{assistant_message}",
64
+ "tool": "{tool_message}"
65
+ },
66
+ "messages": [],
67
+ "seps": [
68
+ "",
69
+ "<\uff5cend\u2581of\u2581sentence\uff5c>"
70
+ ],
71
+ "role_content_sep": "",
72
+ "role_empty_sep": "",
73
+ "stop_str": [],
74
+ "stop_token_ids": [
75
+ 128001
76
+ ],
77
+ "function_string": "",
78
+ "use_function_calling": false
79
+ },
80
+ "pad_token_id": 0,
81
+ "bos_token_id": 128000,
82
+ "eos_token_id": 128001
83
+ }
model.so ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2cc113ed3c787aaa74a6339d8aae761a5e276e34a69e4af0371d455e145a9be
3
+ size 12190536
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 sha256:51e13215b9172a1b4269e342a95e5761437fed7e01374ad36cb6821aef1922ff
3
+ size 262668288
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0f867919ce28d391225eb399b22ffadc63e22788caa392ed97e671f4a58012
3
+ size 32833536
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48aced699b5afc976368a0d207206ce780401106d435df4051c8bd029c25f8ef
3
+ size 21073920
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3feffcef9c8a19beec98df4aebf428abbae8f0d45f6d30c1ae0d1c2703fe01e8
3
+ size 58720256
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93403f37c59b30776e4e671c90573fbd90c1a5f088189f25ffd9e4a8848c4fe7
3
+ size 29360128
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ef0370f88269ac685fb6a896a8dcbccfbd2f3639f6c3c84b5f51ff0281091e
3
+ size 21073920
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da9e192ad27d1eaf29d01d4ec9ba8bb65eeb94a59e9a41babd7c924086cabf6
3
+ size 58720256
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042fa6d982a8f53b6285fbc14b116790b95cd2eba12135a30f76b1234cdfec15
3
+ size 29360128
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ae2a970b7a7d12f81cf0fd35ac4c8810a2a9249ad5e75ffcb861abc499b0ba
3
+ size 21073920
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf0996f5c30c6e3a4ef6ca44bf181da77b54c6a2c1f58bdcc8d159cc0b0838c
3
+ size 58720256
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53fcccd81f2753216e02da44534622d6b2d41cab661f8ca27da46701763196ae
3
+ size 29360128
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951ff4cebf9f0e38dbed1a1ca4679574d8be95d30c6de7cc2ea180792057e840
3
+ size 21073920
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e0f7abbfebd40e14eacf14729b41460811e621a0f49ac63a568dfbed5c0b16
3
+ size 58720256
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a6ff766ee89662900223b53f288b2201d4a1e947ae73ee839c3ca9c96875bf
3
+ size 58720256
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f6a1f4fedd949d827f43deb40d5649cb3650b04d3e2cfe2459f450e60ae890
3
+ size 29360128
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31c8d9cb643362cc58702a5a871a376eb6cee762855d4a91e0fa72fe9a2a88c
3
+ size 21073920
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84400ebf65677adb7851668340adc8e7924861c0b33b8b7540d22d4c7596c6e
3
+ size 58720256
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053d57ead3056562ac67ff009d0427062d2224ff2308fa574f0276f9588af869
3
+ size 29360128
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907d9f2fdba40db29c680058969aa77a57f0341a76dccd0b1de05d1c4a949671
3
+ size 21073920
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34431feb26fbdd1f43d55ad42aac770890840ef4fd702dd2369a32f52cfac230
3
+ size 58720256
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2308319786ad76d37184c4b03b0a50b826fcf0aa5a5cb9773df0d4b8d73c9c62
3
+ size 29360128
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1ebe6d3b9fef538dc2f17fdb7b5361d4d1ac1c3f14fdb42bef7fcd9bb784f7
3
+ size 21073920
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9cceafee6331ddb2be459ce36b9c37b0338919978334aa064ddd060d74767e
3
+ size 58720256
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d7092f6b7f9da0ddc5bccbdd0e56e6b1f4a16d7195b1ab6e8595454b4ecb65
3
+ size 29360128
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6ae51a1fdfab5964ae7431cab7ba1d2cc8ecf35a884623df52eeb91b005d50
3
+ size 29360128
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13561d82129a8a873120927ef79fdcbb2257e8d15b3f911fa749859faf5c9f24
3
+ size 21073920
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72995f6aa0d66bb4602d6a4be6d579be2951fca33e13e208c25ca17b4291bcdf
3
+ size 58720256
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bd41c47d026c2c138d3b82dd89693ff30d895a2009159cdc9e47e4fbb166f7
3
+ size 29360128
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4482da8d6e5d44644b772ff528c86e99827165b825383f017b10c3a7c016794
3
+ size 21073920
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca756909ec4acbca2ad957b6b8840502a39cea67abc0cd1d8ea7c07cd70ed509
3
+ size 58720256
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbd8ff8fb4ee57810af42c6ef235993e5c9fde7ec648867a84216305ee200fb0
3
+ size 29360128
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4700619df1b341a259f3a6d82f3f46e1f96526bda08ddeae3b2ba9d39fde3f2d
3
+ size 21073920
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36867e00e17c9e0ec45fd6863c66105866927d6617e455dfbd8918546e79e5c8
3
+ size 58720256
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf27066e6cd2398d0a907b2121a464cc4ac3e614d1c00d29ff1f4be84f99ac3
3
+ size 29360128
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:255fe50407e144ea506b4d757821a50dedaae370c5e21784f5a9134065106a21
3
+ size 21073920
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907c055e294c303c4bbef1c1d1a8ca425f24effee644cd56c3e5a3062eea2269
3
+ size 21073920
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1a6229241969a9baa403387c6e28c4829bb33c10c73ec077e54c7430423e87
3
+ size 58720256
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60988d34919d295dac98b8adbb4692b6eb3a0bf8f76ef45df6b0c5d2773ff675
3
+ size 29360128
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9de780dae5b5f06dc9d470a5429889ee26d816d3b4eaddf87222e3c56d5781d
3
+ size 21073920
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e88b13fc4d038d4077761971dd70bf9ac4994a06d59c8bc3f932582433ce98
3
+ size 58720256
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6528a7aca367add6b89aa2f6463a8f394879a6937f826434cdcc8130b2ab2d8f
3
+ size 29360128
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b226ff4eea9b58e8af0e03600f14dbe3cfac8d4e02486117636b3fc4f89afd
3
+ size 21073920
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35c4fc2e76c39a32d1ba573e77122ec605eb648fdbd1f880a72c383ad43ec2e
3
+ size 58720256
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be198b561677afecdbbb1e31164a31d525e87ddbd8adfca7e2410c2e9f134a43
3
+ size 29360128