Hugging Face's logo

Jeethu
/
Meta-Llama-3.1-8B-Instruct-PLLM

Text Generation
MLC-LLM
PyTorch
facebook
meta
llama
llama-3
conversational
4-bit precision
Model card Files Community
Jeethu commited on
Commit
20f5b7a
•
1 Parent(s): 5f88c54

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 +21 -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 +1,24 @@
1
  ---
 
 
 
 
 
 
 
 
 
2
  license: llama3.1
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ - de
5
+ - fr
6
+ - it
7
+ - pt
8
+ - hi
9
+ - es
10
+ - th
11
  license: llama3.1
12
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
13
+ base_model_relation: quantized
14
+ library_name: mlc-llm
15
+ pipeline_tag: text-generation
16
+ tags:
17
+ - facebook
18
+ - meta
19
+ - pytorch
20
+ - llama
21
+ - llama-3
22
  ---
23
+
24
+ 4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Meta-Llama-3.1-8B-Instruct](meta-llama/Llama-3.1-8B-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": 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
+ "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 sha256:41a2f4fa1a250ee63170994b042ec48140299b49cb7e8a678b19b5ab1abbe4ea
3
+ size 262668288
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c41b933316e6a070ee9501e1b5fa19623cbd19b957fc0a9a483189f12a5824
3
+ size 29360128
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bba281c1955a579afa7eadbd70970af7f63ba01224254cbc15df5afc6406ad21
3
+ size 29360128
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae7292d8cf8c723f146e3540fc655658cba0d9ad27837ee3e231511755a29d84
3
+ size 58720256
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256d6cffc8121b4d8b3b81a378ac0f76b71fc253daff37b2f064bacdec49c3a7
3
+ size 24395776
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:722e37fac1f36d8bdfb509dcb3de617d18ec26980251150ef5eb43eee5677395
3
+ size 29360128
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0157c48735c4e3f55e3fe20043ce6d1619a5ec15d70f0860376957759507395f
3
+ size 58720256
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf42803d2247e64cd5fe019d08a9eadf3563e14f14762cf3c73cddd7ca537be5
3
+ size 24395776
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d93c4dc89458272addbec0b2974c3d35c29ae1f4ccf14502d1d578be43bd20
3
+ size 29360128
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b12335ca5dd5578e100ccc7b6cd6c1d4005abc4c78c240e22d03222a18f8d8be
3
+ size 58720256
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8edaffed6f4b91c7b6cdf239e51d20dbe82b71e330194612a6dc20ddd0d41ee6
3
+ size 24395776
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a14cedb521cd3951b60d13b0c4e9cd98cf4b3cfaec6a0099969a8f8eaa911db
3
+ size 29360128
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2501fd9a15a52b0f410aa79d19526c7fbbee1211617be51f32aa9263ecc5a701
3
+ size 58720256
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc520cbce8956e00b949697d549fee7b42f968c5ca46f55962b4b098f5edeedc
3
+ size 58720256
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082534261051b9eae874608f4f2b76f2d34e625a43f10cc7fe29e992c3b98e0f
3
+ size 24395776
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a6cb9a2b9f142fd72a69885e1e7c91217407257303c4ce385bb139e53cfedf
3
+ size 29360128
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d14ee0624cdbb3210117c5640fb1accabff2fe76cc0ba7100be437a2e006d73
3
+ size 58720256
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0eab55215792f2a07c8227b5f8451f54c5d77f25fa6c6ec34f0102db0464dae
3
+ size 24395776
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:565e7b77c437f48ca7675960f6ca472079e47d239cc5e23ab621d12622485af7
3
+ size 29360128
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec1b3f2f60b56cf205a8a8440d8f7afc84a21a7f5ed58de412690efe51e7c726
3
+ size 58720256
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c95d3286d2930b46a355d3986a1905bc4d08d9f84a477996b1f21fbf15f9cf2
3
+ size 24395776
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6747b8e9701498cf335a63b75385be78da52038259842dc8db34921742da853a
3
+ size 29360128
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32157f1ec01489bbe1f2741f94500497ed570836782ba04007e3dc2c531198f
3
+ size 58720256
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0990bc03cb157651b6aa4642418cabbbd3a44e9157fc29d922420c2736a0961c
3
+ size 262668288
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0139be689f206d22f1c145a534949367f41d012b4578bd3fe64f760ce2ac7b03
3
+ size 24379392
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84269153e0e6547b9ad230af822398ba5c8ef959ac8aa34ad4ee2ee4557484e0
3
+ size 29360128
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223ad181978c89881388ab84ffa9ccfc353c82bcbdc4a14028e996cb9dfb67f4
3
+ size 58720256
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4dd750e8fd9875c4e84cb3417b9f6fcb66ce31371a35394869f39fd6411165
3
+ size 24395776
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9707fcc0bf550872812d0798c9bca3f63a42f9fdb55f38702d978aab8005d9a6
3
+ size 29360128
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13092a80d62ac652ab084a4bf512d861a21441fe965e5f2b5a2ade805e6c77c5
3
+ size 58720256
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f0024981943f86fc2d206b53e3862e3b7271b09500f314a1319824cc40bc4b
3
+ size 24395776
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbf90c92bb7a72330b4a391f62b501e25f9c0bce1c890c8cecf3e739a7b765c
3
+ size 29360128
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68a5d1f65e039afb384d0c3f008c846193ecae0c940a49aacd03fa58a30f8db
3
+ size 58720256
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b88548b68376ad8714442b2ef69abef37c285c7285312da23d56b4a1c0b5b50
3
+ size 24395776
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1aae1449859ea9c0f2c251459d63bf48aee29e3385e4cac9fb09b081f7bb2f9
3
+ size 29360128
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb32d180f7f618cb769129803ecf3e524908f66576746d74e07cc9cf9add1960
3
+ size 29360128
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0251dfa1266b7cec3d6063cf4501b556fe2cf04640dcaa6ec588156878a069
3
+ size 58720256
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a231fb1144d498e5c77feaba59f1875849ccd43a2a9dd517871fb26a99a4b567
3
+ size 24395776
params_shard_43.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd88a797b95311a13e1f2d76f0d6f7bd65c7e328c61577dc371342b54968b982
3
+ size 29360128
params_shard_44.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff1c34de6a30f5f8a9c0d64ddc467802459a5f659cfe84613b6565bcd46a6ea
3
+ size 58720256
params_shard_45.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5770ee22dd98a76aec9510f2dd2c6f8583d3bff0960d4d12af6694441a9479
3
+ size 24395776
params_shard_46.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2a494fd811ee5861b91873adfda9a9837b83d96a7699611da74e1e0d42af58
3
+ size 29360128
params_shard_47.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc98b512dcc183b7e00712983a9b26c5e59ba4724b4853bc128b30b071c4370
3
+ size 58720256
params_shard_48.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d53df0c530f9d31ccd87f4b55d55f6d5ce6a8a441eaa6458095474faa208fd
3
+ size 24395776
params_shard_49.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9535141390179dbd18dd12e4cc05d07c1adab4f90722d5b144ea63e8f882fbc1
3
+ size 29360128
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93aae83e5e11c8f603d217d1693dd56b94337606f78fa8f3d8a20101e7d4f888
3
+ size 58720256