Hugging Face's logo

Jeethu
/
Llama-3.2-3B-Instruct-PLLM

Text Generation
MLC-LLM
conversational
4-bit precision
Model card Files Community
Jeethu commited on
Commit
559cfe6
•
1 Parent(s): 94668cb

Add weights

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +15 -0
  2. config.json +5 -0
  3. mlc-chat-config.json +90 -0
  4. ndarray-cache.json +0 -0
  5. params_shard_0.bin +3 -0
  6. params_shard_1.bin +3 -0
  7. params_shard_10.bin +3 -0
  8. params_shard_11.bin +3 -0
  9. params_shard_12.bin +3 -0
  10. params_shard_13.bin +3 -0
  11. params_shard_14.bin +3 -0
  12. params_shard_15.bin +3 -0
  13. params_shard_16.bin +3 -0
  14. params_shard_17.bin +3 -0
  15. params_shard_18.bin +3 -0
  16. params_shard_19.bin +3 -0
  17. params_shard_2.bin +3 -0
  18. params_shard_20.bin +3 -0
  19. params_shard_21.bin +3 -0
  20. params_shard_22.bin +3 -0
  21. params_shard_23.bin +3 -0
  22. params_shard_24.bin +3 -0
  23. params_shard_25.bin +3 -0
  24. params_shard_26.bin +3 -0
  25. params_shard_27.bin +3 -0
  26. params_shard_28.bin +3 -0
  27. params_shard_29.bin +3 -0
  28. params_shard_3.bin +3 -0
  29. params_shard_30.bin +3 -0
  30. params_shard_31.bin +3 -0
  31. params_shard_32.bin +3 -0
  32. params_shard_33.bin +3 -0
  33. params_shard_34.bin +3 -0
  34. params_shard_35.bin +3 -0
  35. params_shard_36.bin +3 -0
  36. params_shard_37.bin +3 -0
  37. params_shard_38.bin +3 -0
  38. params_shard_39.bin +3 -0
  39. params_shard_4.bin +3 -0
  40. params_shard_40.bin +3 -0
  41. params_shard_41.bin +3 -0
  42. params_shard_42.bin +3 -0
  43. params_shard_43.bin +3 -0
  44. params_shard_44.bin +3 -0
  45. params_shard_45.bin +3 -0
  46. params_shard_46.bin +3 -0
  47. params_shard_47.bin +3 -0
  48. params_shard_48.bin +3 -0
  49. params_shard_49.bin +3 -0
  50. params_shard_5.bin +3 -0
README.md CHANGED
@@ -1,3 +1,18 @@
1
  ---
 
 
 
 
 
 
 
 
 
2
  license: llama3.2
 
 
 
 
3
  ---
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ - de
5
+ - fr
6
+ - it
7
+ - pt
8
+ - hi
9
+ - es
10
+ - th
11
  license: llama3.2
12
+ base_model: meta-llama/Llama-3.2-3B-Instruct
13
+ base_model_relation: quantized
14
+ library_name: mlc-llm
15
+ pipeline_tag: text-generation
16
  ---
17
+
18
+ 4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct).
config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "quantization_config": {
3
+ "bits": 4
4
+ }
5
+ }
mlc-chat-config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "w4a16g128",
5
+ "model_config": {
6
+ "hidden_size": 3072,
7
+ "intermediate_size": 8192,
8
+ "num_attention_heads": 24,
9
+ "num_hidden_layers": 28,
10
+ "rms_norm_eps": 1e-05,
11
+ "vocab_size": 128256,
12
+ "tie_word_embeddings": true,
13
+ "position_embedding_base": 500000.0,
14
+ "rope_scaling": {
15
+ "factor": 32.0,
16
+ "high_freq_factor": 4.0,
17
+ "low_freq_factor": 1.0,
18
+ "original_max_position_embeddings": 8192,
19
+ "rope_type": "llama3"
20
+ },
21
+ "context_window_size": 8192,
22
+ "prefill_chunk_size": 128,
23
+ "num_key_value_heads": 8,
24
+ "head_dim": 128,
25
+ "tensor_parallel_shards": 1,
26
+ "pipeline_parallel_stages": 1,
27
+ "max_batch_size": 128
28
+ },
29
+ "vocab_size": 128256,
30
+ "context_window_size": 8192,
31
+ "sliding_window_size": -1,
32
+ "prefill_chunk_size": 128,
33
+ "attention_sink_size": -1,
34
+ "tensor_parallel_shards": 1,
35
+ "pipeline_parallel_stages": 1,
36
+ "temperature": 0.6,
37
+ "presence_penalty": 0.0,
38
+ "frequency_penalty": 0.0,
39
+ "repetition_penalty": 1.0,
40
+ "top_p": 0.9,
41
+ "tokenizer_files": [
42
+ "tokenizer.json",
43
+ "tokenizer_config.json"
44
+ ],
45
+ "tokenizer_info": {
46
+ "token_postproc_method": "byte_level",
47
+ "prepend_space_in_encode": false,
48
+ "strip_space_in_decode": false
49
+ },
50
+ "conv_template": {
51
+ "name": "llama-3_1",
52
+ "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
53
+ "system_message": "You are a helpful, respectful and honest assistant.",
54
+ "system_prefix_token_ids": [
55
+ 128000
56
+ ],
57
+ "add_role_after_system_message": true,
58
+ "roles": {
59
+ "user": "<|start_header_id|>user",
60
+ "assistant": "<|start_header_id|>assistant",
61
+ "tool": "<|start_header_id|>ipython"
62
+ },
63
+ "role_templates": {
64
+ "user": "{user_message}",
65
+ "assistant": "{assistant_message}",
66
+ "tool": "{tool_message}"
67
+ },
68
+ "messages": [],
69
+ "seps": [
70
+ "<|eot_id|>"
71
+ ],
72
+ "role_content_sep": "<|end_header_id|>\n\n",
73
+ "role_empty_sep": "<|end_header_id|>\n\n",
74
+ "stop_str": [],
75
+ "stop_token_ids": [
76
+ 128001,
77
+ 128008,
78
+ 128009
79
+ ],
80
+ "function_string": "",
81
+ "use_function_calling": false
82
+ },
83
+ "pad_token_id": 0,
84
+ "bos_token_id": 128000,
85
+ "eos_token_id": [
86
+ 128001,
87
+ 128008,
88
+ 128009
89
+ ]
90
+ }
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 sha256:7f3e46493b42f3b526c7de905eb25a776314c4fed99dbfa825421fc0e3d587e1
3
+ size 197001216
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba87ceec2d8d53478be3a918b1f83480e0f9bc744e5f035516946beccfeb289c
3
+ size 25165824
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:106b14b8d7edb42acbaf2a889a1eac1517f1126fe6b36eef84a807bf41aaffec
3
+ size 26750976
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f493309bfe0719899af90a397cfe3e4d1884e899ce75b4ece95879420d40e31
3
+ size 25165824
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e9f76f7db33937af9006b827990e8a6004533e9d3da0cabbc3f8413788d8dc
3
+ size 26750976
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6af1724b1c780287f7bac5c4ce8452e44ad702b6bc435cb08bbdf4645ff2ba0
3
+ size 25165824
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8d2d9f34e25bf7885056a6392ec2721601fc6ce80287d67782c66b310f93abf
3
+ size 26750976
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3838e019db8379ad3c8d4ca5a00f0cfbeb22cf22ef9065a59946c470127c295b
3
+ size 25165824
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4828b4b668d8b10448d4239b12573fe11700958d2868e72955e31596b89175b3
3
+ size 26750976
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05c6604c2ce01344d115a2cf9d7ec1b6daf8106ff75c98e96635b20735e255f5
3
+ size 25165824
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178c58d8659a4f52c880c81f1ef507bf906aeaa74191b4e67d02004b1a8e0a42
3
+ size 26750976
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb3b459a2590ac1ff79c7bbe42878c8c9718889ad937a5079d22fb301b5523e
3
+ size 25165824
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015abfc1af8ceb75e2bee41b89b62c474b5de1245de452af149e8ffc7cbe3105
3
+ size 32913408
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e30999d85ace828e8be3581658204db86e2ee2ee0339e207f2c85325ed195a
3
+ size 26750976
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92fb5332e971c43cda3920d284dd799e78a773785b65fccafa7c930380b893b
3
+ size 25165824
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ea666a57d22710a72de48634dafde318ba8140342928956e39654f58d4d342e
3
+ size 26750976
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c636c94cfcf5cd38e3816674cfe2db16e91873e91ec3225a931808b6675325
3
+ size 25165824
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5fc93f3798449682bbeb0916828de1f0925860dad80d6803c15b40606794287
3
+ size 26750976
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5100de9f1abc8bd255bc6a113a6196dfd98e801a231649d8d0d51c58ea966b0f
3
+ size 25165824
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0005000619cc8373eef6a71db56324f7b70eac0438017d9cc693ea654319eff
3
+ size 25165824
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63068bb9a450a51c85c10289957b5b18a925198894f3b3b5703d241e71822c9b
3
+ size 27531264
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0fa15737dcde3dac36b96616a409a27c5102ddb7d1c0d1b89d54be610b83e46
3
+ size 25165824
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855f8f91b7d78b1d2b278a625ed73d6df8fd2470cd37ee94ce7fcadb84b11d46
3
+ size 26750976
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876d13e502eec0702a6a80ac001481d0e89448bd195f21f30479c61457fcff28
3
+ size 25165824
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1121b72708c58cb0b106fb143fac20cb60f993899790041ec078624ad331a49
3
+ size 25165824
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8daf3035d170007d97d6941c6562a945481e5c0448bf27dd174b8b6bb5f1329d
3
+ size 26750976
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c43e52ee64f6cb43647a5be89bae66fd1e3702bf29a10a379f9efd31a53d258a
3
+ size 25165824
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210df6dc89ba988b2296298952b4f54acca3429e06d6442df7608a1a39a4382c
3
+ size 26750976
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1616e31f03714be5627f3b78eee47bf7f4f1db3fcb9205a3b1397ebf473aff7
3
+ size 25165824
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c48703478831cf599d7293af142b9b43bcf581f594c7c31946eadbaf351f411f
3
+ size 26750976
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711a207e46aaa1d742ebad28a786a4359047e974db46ba4ae860361d8184f9f5
3
+ size 25165824
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e5f6056ab6ee8f64a2766ac156c1e2d4292b1478f681ab3f20a96b53e19c414
3
+ size 26750976
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93b0f3eadef68dad75d3b4f9cd1d701ce033cb79516f38763349009763952300
3
+ size 25165824
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd6c7b03b1cf6ee02474596192e468b8a1e108082c86476e50bfb7316a57c17
3
+ size 26750976
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60741e51f4b5e0b5cd66157f5d990788e6f307a6ffe1d890c3ab0a6f7745e5fe
3
+ size 26750976
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f12b276f1c5234d7a33d6a03bc8ef1d46fb7648d056f0cd66560ae05d1ec0f
3
+ size 25165824
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f8a92bef5b0fcfff92c4db3f2331cbb5e8a4eae14d9af0870056bdb991d88b
3
+ size 26750976
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7f1a37ba44f84b76f065b0c215bfab82eeb2bb16570aa0d25dcdda80927bb8
3
+ size 25970688
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76cc54cd23110ac1d181c4a0f9a18ed4b62b2f7832088de92dc221e6f14d7a7
3
+ size 25165824
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff00fabeb88dd77acb2d9e5ef807cb0cf5b2bd87f62d41223e46e48a470157d
3
+ size 26750976
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d248d761eb758c558eb4a18579feb1c3e6f06f37d46f5acf6d3a1841596ccbcf
3
+ size 25165824
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44187b95a5b9eca01ed466049b66dea58f0d5c2755bc13b309e49f8132269dbc
3
+ size 26750976
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41acc6c9842d99dcfcb6081ffa98edb866fbe6a4f16e2dcda6a4f99c3826ac38
3
+ size 25165824
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b41726d09205d81fa41bed8c40017182117b96a18addf88777ccfa396b7dd850
3
+ size 26750976
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec9b06b116587069ebb7666350622cc500f06cb65729cd362a928a04dd01dc5
3
+ size 25165824
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66358c9b4123705c3419e117b72e5b3b310375f1e1663e66eba93fbe8e0764a2
3
+ size 25165824