Hugging Face's logo

pr0methium
/
ReelevateLM-q4f16_1

MLC-LLM
web-llm
llama-3.1
instruct
q4f16_1
Model card Files
xet
Community
premalt commited on
Commit
fe1e798
·
1 Parent(s): a964b6f

Add model 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. .DS_Store +0 -0
  2. README.md +60 -1
  3. mlc-chat-config.json +91 -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_100.bin +3 -0
  9. params_shard_101.bin +3 -0
  10. params_shard_102.bin +3 -0
  11. params_shard_103.bin +3 -0
  12. params_shard_104.bin +3 -0
  13. params_shard_105.bin +3 -0
  14. params_shard_106.bin +3 -0
  15. params_shard_107.bin +3 -0
  16. params_shard_11.bin +3 -0
  17. params_shard_12.bin +3 -0
  18. params_shard_13.bin +3 -0
  19. params_shard_14.bin +3 -0
  20. params_shard_15.bin +3 -0
  21. params_shard_16.bin +3 -0
  22. params_shard_17.bin +3 -0
  23. params_shard_18.bin +3 -0
  24. params_shard_19.bin +3 -0
  25. params_shard_2.bin +3 -0
  26. params_shard_20.bin +3 -0
  27. params_shard_21.bin +3 -0
  28. params_shard_22.bin +3 -0
  29. params_shard_23.bin +3 -0
  30. params_shard_24.bin +3 -0
  31. params_shard_25.bin +3 -0
  32. params_shard_26.bin +3 -0
  33. params_shard_27.bin +3 -0
  34. params_shard_28.bin +3 -0
  35. params_shard_29.bin +3 -0
  36. params_shard_3.bin +3 -0
  37. params_shard_30.bin +3 -0
  38. params_shard_31.bin +3 -0
  39. params_shard_32.bin +3 -0
  40. params_shard_33.bin +3 -0
  41. params_shard_34.bin +3 -0
  42. params_shard_35.bin +3 -0
  43. params_shard_36.bin +3 -0
  44. params_shard_37.bin +3 -0
  45. params_shard_38.bin +3 -0
  46. params_shard_39.bin +3 -0
  47. params_shard_4.bin +3 -0
  48. params_shard_40.bin +3 -0
  49. params_shard_41.bin +3 -0
  50. params_shard_42.bin +3 -0
.DS_Store ADDED
Binary file (14.3 kB). View file
 
README.md CHANGED
@@ -1,3 +1,62 @@
1
  ---
2
- license: cc0-1.0
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+
3
+ library\_name: pr0methium/ReelevateLM-q4f16
4
+ base\_model: meta-llama/Meta-Llama-3.1-8B-Instruct
5
+ tags:
6
+
7
+ * mlc-llm
8
+ * web-llm
9
+ * llama-3.1
10
+ * instruct
11
+ * q4f16
12
+
13
  ---
14
+
15
+ # ReelevateLM-q4f16
16
+
17
+ This is the [Meta Llama 3.1 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) model fine‑tuned with LoRA and converted to MLC format `q4f16_1`.
18
+
19
+ The model can be used in:
20
+
21
+ * [MLC-LLM](https://github.com/mlc-ai/mlc-llm)
22
+ * [WebLLM](https://github.com/mlc-ai/web-llm)
23
+
24
+ ## Example Usage
25
+
26
+ Before running any examples, install MLC LLM by following the [installation documentation](https://llm.mlc.ai/docs/install/mlc_llm.html#install-mlc-packages).
27
+
28
+ ### Chat (CLI)
29
+
30
+ ```bash
31
+ mlc_llm chat HF://pr0methium/ReelevateLM-q4f16
32
+ ```
33
+
34
+ ### REST Server
35
+
36
+ ```bash
37
+ mlc_llm serve HF://pr0methium/ReelevateLM-q4f16
38
+ ```
39
+
40
+ ### Python API
41
+
42
+ ```python
43
+ from mlc_llm import MLCEngine
44
+
45
+ model = "HF://pr0methium/ReelevateLM-q4f16"
46
+ engine = MLCEngine(model)
47
+
48
+ for response in engine.chat.completions.create(
49
+ messages=[{"role": "user", "content": "Write me a 30 second reel story…"}],
50
+ model=model,
51
+ stream=True,
52
+ ):
53
+ for choice in response.choices:
54
+ print(choice.delta.content, end="", flush=True)
55
+ print()
56
+
57
+ engine.terminate()
58
+ ```
59
+
60
+ ## Documentation
61
+
62
+ For more information on the MLC LLM project, please visit the [docs](https://llm.mlc.ai/docs/) and the [GitHub repo](https://github.com/mlc-ai/mlc-llm).
mlc-chat-config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "llama",
4
+ "quantization": "q4f16_1",
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": 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": 128,
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": 0.9,
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": "llama-3_1",
53
+ "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
54
+ "system_message": "You are a helpful, respectful and honest assistant.",
55
+ "system_prefix_token_ids": [
56
+ 128000
57
+ ],
58
+ "add_role_after_system_message": true,
59
+ "roles": {
60
+ "user": "<|start_header_id|>user",
61
+ "assistant": "<|start_header_id|>assistant",
62
+ "tool": "<|start_header_id|>ipython"
63
+ },
64
+ "role_templates": {
65
+ "user": "{user_message}",
66
+ "assistant": "{assistant_message}",
67
+ "tool": "{tool_message}"
68
+ },
69
+ "messages": [],
70
+ "seps": [
71
+ "<|eot_id|>"
72
+ ],
73
+ "role_content_sep": "<|end_header_id|>\n\n",
74
+ "role_empty_sep": "<|end_header_id|>\n\n",
75
+ "stop_str": [],
76
+ "stop_token_ids": [
77
+ 128001,
78
+ 128008,
79
+ 128009
80
+ ],
81
+ "function_string": "",
82
+ "use_function_calling": false
83
+ },
84
+ "pad_token_id": 0,
85
+ "bos_token_id": 128000,
86
+ "eos_token_id": [
87
+ 128001,
88
+ 128008,
89
+ 128009
90
+ ]
91
+ }
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:a67884213c3cc8b6fc2c3ae8a2c19a15403cd6fc048a04816dd03e8ebd4faf30
3
+ size 262668288
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aeb816081f5ee4689d79ac9286ee6237d120b83dbcae5e5d3932fcc988eb573
3
+ size 29360128
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5fc0f24a7b042e6b974482bdc6d5531e537a7388c2054f8ed2cd81c26df6ef7
3
+ size 33046528
params_shard_100.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b26961759829d475c6875451edc62a1842e7dc04e1678a045f16671fc1141f
3
+ size 58720256
params_shard_101.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48df3969c26f320051b022630d8182847a2195f9679c926a6139ef9dc50df625
3
+ size 25174016
params_shard_102.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba025ba95cbd20c578d29ba89593142dd7c5cec5d576dc14b261b8db272e2873
3
+ size 29360128
params_shard_103.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6b595e0e3c9a27fd2cfcf723b3ebdfe0a1b3ab015c100ae5ce583fdbde66b7
3
+ size 58720256
params_shard_104.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37688f0688cdf62b0c8e68e6a07e84b992323a841d8ecdb99ee78612ae0cd29e
3
+ size 33046528
params_shard_105.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a671d0077476f691c0010cf2b8a3abc683ed3cce2956a0fd8a775ec28d04a43
3
+ size 58720256
params_shard_106.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfae0b0773370e7ddb435b25117d9175ed15a1c751804c66419f41262f53718e
3
+ size 32505856
params_shard_107.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b8809b83415ea588740f9c0e006aadd4c3eee22bd93bdc5786aefa0b8ca830
3
+ size 9437184
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:444f61705327765424205007f561553fa8489426e34b401439e9e12832858678
3
+ size 29360128
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010229d346ed66c55c411e05e85722f54c6212192b4f8a607ed785085d6fe102
3
+ size 58720256
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c791f44b669c1e097062f8b7a0ddf2007aaff6bd86e087689d4dc6cb11d74bbd
3
+ size 22036480
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f616ea33b6ffde4c650f49dcc694573d1cf913d8d4c049b6cd3484b8f76bbd
3
+ size 29360128
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1165f342f68ff91a887b8582ca880a4d8d78a1fc4ad1f9eb62f6e35acf7da6
3
+ size 58720256
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae96ecd9b3a3af9b4961867dd55c3583c108918a5f3cb2c9ef7cec9bcf31b78b
3
+ size 27271168
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d55b6488ace4c344d0dd1112ff53e3fa255eadf266b2ddc584c2cc8733320b
3
+ size 29360128
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b419b7015a8c3155ce6055a4a14b5430b919ef4dac67aea6b653a384b135d793
3
+ size 30949376
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35ae3bbd9b62f5cdecc444f2aa62f54736ab9768de060436678c25c96447f92
3
+ size 58720256
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a01095032dc8e6fce9f2b5628799d1bd2cf715ea1db5c2780ab599e0b45578
3
+ size 32841728
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be49b60cb3486dbafe9078844730e0aa6511f4df6c298b4fa900e53ae8e8306
3
+ size 25174016
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beab46023d308dcf29a01156f8da18b9f1a56f7c6ab395190b6f2141c4beed2b
3
+ size 29360128
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55941e4f10fb78da3417f5d64147122de321216cfbc1eff9ff8ca9034fcf73f5
3
+ size 58720256
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b3328f9803acdf13a268f79a636661fe401268bfbc7b89cf03cf6eaefbf357
3
+ size 33046528
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4deb86cb1497752a34a5c45dce3f4911113a9d7cd012a3c6568ebe9b7c6bc7
3
+ size 29360128
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74eaaf46ea7092dfe3d1980abadd53223729b0bb465808d1bf40e0334a0d8d7
3
+ size 58720256
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478dc682dc70d9fde6f5acb42490500be7a6b2c365c013f81990a48ddde9a3aa
3
+ size 22036480
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7f64f6c39250815e1516f10db114e334088f159fd77f5737b420c860d0a500
3
+ size 29360128
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3a0d683ae8a9c99c9c45ab41c5422ee4113c24d5e20356c28bf9a34495036d
3
+ size 58720256
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1a003f3ae26b5c79791ed64d87b7bc5f41752c2e831e4fe5db3d5b38b3887e1
3
+ size 27271168
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c60f308cb17fb4bf96ab295b3db1595da53adb3cf628c547a2f1e537d15044
3
+ size 262668288
params_shard_30.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a704eac5929bee6ecb8e9c8c806da39d74dba3ecb45f7517741fd89cc9d330bf
3
+ size 29360128
params_shard_31.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5798f9d9a8b1eb0ad3ed5a7d840447997a512621c235a0b2f78d823cac48185d
3
+ size 30949376
params_shard_32.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30eb042156b3cf9dee15808ccfffda00d1295e56c39f743bc318e2a22a39c40
3
+ size 58720256
params_shard_33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d881cfc96450e364df1da51400d571503ce5c1099bbf4e267f8591ec12808e6
3
+ size 25174016
params_shard_34.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7585e5b1935bc764484a106292ead441e269a5fbdd13f0cb50597bd33fdf36e1
3
+ size 29360128
params_shard_35.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:912f2612a30890437f358d510a46b19a3301586525ee64a266061e9d0b69e24a
3
+ size 58720256
params_shard_36.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad2cba595961d903026b2fbcadfac2d141ede1b9b268dcf0548eebb62acdc4e
3
+ size 33046528
params_shard_37.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa245a0da04870562a31a2a1a80a1fd0e485c4b08ce7f23f09917c5a8b4bd79
3
+ size 29360128
params_shard_38.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:650459a34e7429cefff7cfde80474f0d682f13a03b912a589695eadaee1d2172
3
+ size 58720256
params_shard_39.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3457ecd8a55b15fbad880d8e7aabf75db1b542e33346746640014eedf7113cdd
3
+ size 22036480
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93686dc4245e85f12cc20b2679458614c2ed2ca33383eeb650984c4116f62401
3
+ size 32833536
params_shard_40.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf0a1219b1111222d82332cee062ce520a62d3fa66fe81f228cb8cfbc949c25
3
+ size 29360128
params_shard_41.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5302a16684ae6f51637b997c238e6bf75c3a2be425d69a6f79e9e42a56700a
3
+ size 58720256
params_shard_42.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbcd8d05daec070c0646b5fdde9dd0d2ba02ad317595d298ccaef1dcb5c92b0
3
+ size 27271168