hyunsikc commited on
Commit
355c1a0
·
verified ·
1 Parent(s): 61640f3

Add files using upload-large-folder tool

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 +9 -0
  2. 017354a37f5a719cb194553947358e14.edf +3 -0
  3. 01fe7ae4d82c193afa32f99296778d78.edf +3 -0
  4. 060031ba550862936ffb24a5f3ccfc52.edf +3 -0
  5. 0ae06be5cf9172521dba3cba07b131a3.edf +3 -0
  6. 1193f984988d3ee989174abf731b99af.edf +3 -0
  7. 154749036dd585efde05dd70ce81181f.edf +3 -0
  8. 1c25e9c7a6da8758352f353fbdb8c489.edf +3 -0
  9. 1c76337161ff37e70f9d9a452eab8bf4.edf +3 -0
  10. 26a39e88d972a5bfbf6aa8261a347005.edf +3 -0
  11. 2b645fbf29fec00c51f855b25e1854df.edf +3 -0
  12. 577a5a794963b4f99c6e20d8bdd15304.edf +3 -0
  13. 614c722425c10b0d7083f77f70e67bb3.edf +3 -0
  14. 61c1ead780ffd881a8dc5d9d68e9132f.edf +3 -0
  15. 673089ec3f7afd2ecc330a11d380e62e.edf +3 -0
  16. 6f802016fb473eb67b524d9e8331d9c3.edf +3 -0
  17. 803454dcfa7655aa36ff084746d5bedc.edf +3 -0
  18. 82113875f7fc69978c25c8040684d297.edf +3 -0
  19. 8f3fc6afa12d521d5edbe2fe68787275.edf +3 -0
  20. 906a586b6fc90a242afc1db2f21458f5.edf +3 -0
  21. 90f930198fef1d2935e911715a6bf548.edf +3 -0
  22. 96718fbad4b07677f215fc2d7fc5e79b.edf +3 -0
  23. 97be6979771a4514772a53c193dbc36a.edf +3 -0
  24. 9c9e5f2ecc027c911ddab078028c5c9d.edf +3 -0
  25. 9cc528a841e6b0fad29953b275563d36.edf +3 -0
  26. 9ef68a950c540ec639bd4c12b54b33b9.edf +3 -0
  27. 9fd8e42148451e15b50364e62e722a7a.edf +3 -0
  28. LICENSE +49 -0
  29. README.md +48 -0
  30. a2cfda531c47c784493091589418b3d5.edf +3 -0
  31. ad4fd37a207b49a373eb6368d3987a1d.edf +3 -0
  32. b11185f6088119736d000dd247cff1dd.edf +3 -0
  33. b2c79ef4862fdf2150460bd532b843a3.edf +3 -0
  34. c3a07812c85ce39a3941013bd5ff843d.edf +3 -0
  35. c5fa247beb9d2d9fc4905ca6acd69625.edf +3 -0
  36. c68545b8dbb6db084ac23c2d5d23cee3.edf +3 -0
  37. ca40627786578d5d970628ea31bf6c71.edf +3 -0
  38. cf40301094ea1602d0e6dbcb86175f90.edf +3 -0
  39. config.json +41 -0
  40. d34c4cdb4d23b46bfed727144031f8f1.edf +3 -0
  41. d58b9a6bcdd4cb2029134bbc98ea5ac0.edf +3 -0
  42. d83e6614984530560e1f58d3926f6299.edf +3 -0
  43. dec1fe274c5d4eb04e7180793f4a4356.edf +3 -0
  44. ee35268bd794c72328a4e74610bdbee0.edf +3 -0
  45. f0300e102621d05ce20fa53c29d82aa5.edf +3 -0
  46. f0b27ab0212685b41bcf7a07a6a6333c.edf +3 -0
  47. f11a4e51b9ea78e15ab75b3cd5ea91b2.edf +3 -0
  48. fa1734ff4313a29966f963dde2d9f6c5.edf +3 -0
  49. furiosa_config.json +58 -0
  50. special_tokens_map.json +17 -0
.gitattributes CHANGED
@@ -137,3 +137,12 @@ f2086571ab760676caa5f4b6a2e64be7.edf filter=lfs diff=lfs merge=lfs -text
137
  d83e6614984530560e1f58d3926f6299.edf filter=lfs diff=lfs merge=lfs -text
138
  d3fe6b56d4dec3703a063e32357e4f66.edf filter=lfs diff=lfs merge=lfs -text
139
  afcf5fe7d18d29a8b68848615e5f9500.edf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
137
  d83e6614984530560e1f58d3926f6299.edf filter=lfs diff=lfs merge=lfs -text
138
  d3fe6b56d4dec3703a063e32357e4f66.edf filter=lfs diff=lfs merge=lfs -text
139
  afcf5fe7d18d29a8b68848615e5f9500.edf filter=lfs diff=lfs merge=lfs -text
140
+ 1c76337161ff37e70f9d9a452eab8bf4.edf filter=lfs diff=lfs merge=lfs -text
141
+ 0ae06be5cf9172521dba3cba07b131a3.edf filter=lfs diff=lfs merge=lfs -text
142
+ f11a4e51b9ea78e15ab75b3cd5ea91b2.edf filter=lfs diff=lfs merge=lfs -text
143
+ 01fe7ae4d82c193afa32f99296778d78.edf filter=lfs diff=lfs merge=lfs -text
144
+ 154749036dd585efde05dd70ce81181f.edf filter=lfs diff=lfs merge=lfs -text
145
+ f0b27ab0212685b41bcf7a07a6a6333c.edf filter=lfs diff=lfs merge=lfs -text
146
+ ee35268bd794c72328a4e74610bdbee0.edf filter=lfs diff=lfs merge=lfs -text
147
+ d34c4cdb4d23b46bfed727144031f8f1.edf filter=lfs diff=lfs merge=lfs -text
148
+ 017354a37f5a719cb194553947358e14.edf filter=lfs diff=lfs merge=lfs -text
017354a37f5a719cb194553947358e14.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f461bf28b2fe78b236a291717ae918bd0a289001d733c587c7595ce82228992
3
+ size 30385671
01fe7ae4d82c193afa32f99296778d78.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d58bcbe628a5f23b9d0009b89277472653f8bc0c33a6a16cb217e3898cc1c0
3
+ size 57086457
060031ba550862936ffb24a5f3ccfc52.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ee4f0dbc840817b18ff8a1bbba84883b0fac604cc1b609f8d6decef0123f15
3
+ size 17334531
0ae06be5cf9172521dba3cba07b131a3.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5693b95b79b1a3cb087446b11a1b926f2ed50669b94edcf95ef2f4dd6190bdd6
3
+ size 56547656
1193f984988d3ee989174abf731b99af.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db2325ae2f73ed6dbdfec99dda4f1d85a98117db96f0dbc8d59c0d5cee52264
3
+ size 3952856
154749036dd585efde05dd70ce81181f.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a03780decedc5f89ff37e982f1a2af2acc4f5fe799e27b66f0d456d20a87ac
3
+ size 56487158
1c25e9c7a6da8758352f353fbdb8c489.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d25520b76e5f353fdfe89f0b5da5f36c8911283dfcb398fe88dd53c6fcef7d4
3
+ size 4758394
1c76337161ff37e70f9d9a452eab8bf4.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c23256ec4bb85e85fcafcdeb43cfc4547508a9f694183ef7327cffb18066138
3
+ size 31098303
26a39e88d972a5bfbf6aa8261a347005.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7788418a209ded8decea81be35662989057a328cb71de47a4822209a959cffe2
3
+ size 3451367
2b645fbf29fec00c51f855b25e1854df.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155a01b7aaf2608bb174b44e4b369a8fbe7ca25ef0f94d9c71d0a42656933877
3
+ size 4797965
577a5a794963b4f99c6e20d8bdd15304.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4b8c5adf6c96e55f3fec886bfe9621cd3b49a1eec830c31cbfc2d139d0d0ab
3
+ size 17097188
614c722425c10b0d7083f77f70e67bb3.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26973587e864fc72d43dc20adaec48301350726d6a11adb3bf6014279b790ccb
3
+ size 5266276
61c1ead780ffd881a8dc5d9d68e9132f.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e918878a3fbf3e46345ce590f079fd5bb2b856a16faeb1e66c9311dcf00b322f
3
+ size 21712791
673089ec3f7afd2ecc330a11d380e62e.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b113946a55c18b2b4bf3c844eeaa72c8ac822d74339afd8f26474143ccd2c85
3
+ size 4298331
6f802016fb473eb67b524d9e8331d9c3.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce4e0ff08518dc99bd97d94cbabe2ffbe58ad247eae44e7d86fa0d90c14e58df
3
+ size 20531472
803454dcfa7655aa36ff084746d5bedc.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7bb772c69baec462fbbf1b93db012e3a283b1e6a0d4111f89caa8e1f8f88420
3
+ size 10937162
82113875f7fc69978c25c8040684d297.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef074b5b44e33657e760caa8941387d55a8a964632558cae90e873fe161ec7f
3
+ size 5291747
8f3fc6afa12d521d5edbe2fe68787275.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57caf31642441bcdd95b0b7e18162cd6ef391eb817b6e545b19f6a432bbac263
3
+ size 4420056
906a586b6fc90a242afc1db2f21458f5.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f715ba90cbb9af5d3ab10983c021ebd921e45b00d6532200363136de3dd3e804
3
+ size 10935633
90f930198fef1d2935e911715a6bf548.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95956f4677a257c37f87b4ab1ba9fcfc10324ba8851a8ad9de0e44868725649
3
+ size 5244774
96718fbad4b07677f215fc2d7fc5e79b.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4638a9106f5b2206a0859ab47ac428ca30b7592ffb569dd7680b29c87e1c633d
3
+ size 17738975
97be6979771a4514772a53c193dbc36a.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1347cf56df082f1187bb4654d564ae631e15765811d8237f47355f56b638d1a2
3
+ size 8583616
9c9e5f2ecc027c911ddab078028c5c9d.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f295fd5224e39100097abf4f1da078e4074d84f0cde45bfb57b43b4c797f988
3
+ size 4894690
9cc528a841e6b0fad29953b275563d36.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e6ea511c31e33a509c4b42299fa57b3c8d9de482d12c1fb519edfdce389a4c
3
+ size 33324700
9ef68a950c540ec639bd4c12b54b33b9.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a28061993969c190f70d721532aa0b1a7414a964a43801aaf9ce2e17b34bd6f
3
+ size 35948341
9fd8e42148451e15b50364e62e722a7a.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867438ea29001a6767cce71273e229b7797c94678231d5d51a646a6888eb4c32
3
+ size 30587358
LICENSE ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ **LLAMA 3.3 COMMUNITY LICENSE AGREEMENT**
2
+
3
+ Llama 3.3 Version Release Date: December 6, 2024
4
+
5
+ “**Agreement**” means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.
6
+
7
+ “**Documentation**” means the specifications, manuals and documentation accompanying Llama 3.3 distributed by Meta at [https://www.llama.com/docs/overview](https://llama.com/docs/overview).
8
+
9
+ “**Licensee**” or “**you**” means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.
10
+
11
+ “**Llama 3.3**” means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at [https://www.llama.com/llama-downloads](https://www.llama.com/llama-downloads).
12
+
13
+ “**Llama Materials**” means, collectively, Meta’s proprietary Llama 3.3 and Documentation (and any portion thereof) made available under this Agreement.
14
+
15
+ “**Meta**” or “**we**” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
16
+
17
+ By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials, you agree to be bound by this Agreement.
18
+
19
+ 1\. **License Rights and Redistribution**.
20
+
21
+ a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.  
22
+
23
+ b. Redistribution and Use.  
24
+
25
+ i. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service (including another AI model) that contains any of them, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama” on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include “Llama” at the beginning of any such AI model name.
26
+
27
+ ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you. 
28
+
29
+ iii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “Llama 3.3 is licensed under the Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.”
30
+
31
+ iv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at [https://www.llama.com/llama3\_3/use-policy](https://www.llama.com/llama3_3/use-policy)), which is hereby incorporated by reference into this Agreement.
32
+   
33
+ 2\. **Additional Commercial Terms**. If, on the Llama 3.3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
34
+
35
+ 3**. Disclaimer of Warranty**. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
36
+
37
+ 4\. **Limitation of Liability**. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
38
+
39
+ 5\. **Intellectual Property**.
40
+
41
+ a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at [https://about.meta.com/brand/resources/meta/company-brand/](https://about.meta.com/brand/resources/meta/company-brand/)[)](https://en.facebookbrand.com/). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.
42
+
43
+ b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.
44
+
45
+ c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.
46
+
47
+ 6\. **Term and Termination**. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement. 
48
+
49
+ 7\. **Governing Law and Jurisdiction**. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement. 
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.3-70B-Instruct
3
+ language:
4
+ - en
5
+ - fr
6
+ - it
7
+ - pt
8
+ - hi
9
+ - es
10
+ - th
11
+ - de
12
+ license: llama3.3
13
+ pipeline_tag: text-generation
14
+ library_name: furiosa-llm
15
+ tags:
16
+ - furiosa-ai
17
+ - llama
18
+ - llama-3
19
+ ---
20
+ # Model Overview
21
+ - **Model Architecture:** Meta-Llama-3
22
+ - **Input:** Text
23
+ - **Output:** Text
24
+ - **Model Optimizations:**
25
+ - **Maximum Context Length:** 32k tokens
26
+ - Maximum Prompt Length: 32768 tokens
27
+ - Maximum Generation Length: 32768 tokens
28
+ - **Intended Use Cases:** Intended for commercial and non-commercial use. Same as [Meta-Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), this models is intended for assistant-like chat.
29
+ - **Release Date:** 07/28/2025
30
+ - **Version:** v2025.3
31
+ - **License(s):** [Llama3.3](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct/blob/main/LICENSE)
32
+ - **Supported Inference Engine(s):** Furiosa LLM
33
+ - **Supported Hardware Compatibility:** FuriosaAI RNGD
34
+ - **Preferred Operating System(s):** Linux
35
+ - **Quantization:** No
36
+ - **Datasets:**
37
+
38
+
39
+ ## Description:
40
+ This model is the pre-compiled version of the [Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), which is an auto-regressive language model that uses an optimized transformer architecture.
41
+
42
+ ## Usage
43
+
44
+ To run this model with [Furiosa-LLM](https://developer.furiosa.ai/latest/en/furiosa_llm/intro.html), follow the example command below after [installing Furiosa-LLM and its prerequisites](https://developer.furiosa.ai/latest/en/getting_started/furiosa_llm.html#installing-furiosa-llm).
45
+
46
+ ```sh
47
+ furiosa-llm serve furiosa-ai/Llama-3.3-70B-Instruct
48
+ ```
a2cfda531c47c784493091589418b3d5.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:282d67871e0c02b4670360f467723643399c536826a17975c067aff36dee50e6
3
+ size 17355102
ad4fd37a207b49a373eb6368d3987a1d.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f19e637b29d743cd4de0862dfaefadfd62b3074761d28aab6d32de7f35535a
3
+ size 21630402
b11185f6088119736d000dd247cff1dd.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaca7ce28fae02766e4c969882a69b7bc9879da429e58a7de4755ac335888c60
3
+ size 17295802
b2c79ef4862fdf2150460bd532b843a3.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8f336c7afb9dc04d00ebebe28a996213b436470b348c34a390497f6cb8cfec
3
+ size 19038895
c3a07812c85ce39a3941013bd5ff843d.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8072c7b5720cf50639df533209b34b4d3eaec78e093fe8d9942752663d8abbfc
3
+ size 4328357
c5fa247beb9d2d9fc4905ca6acd69625.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e595ab3a64f711799c9cd878cb7579d0145db5ef5d18748658dc909d92f73a94
3
+ size 4797474
c68545b8dbb6db084ac23c2d5d23cee3.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8295c3ca801685d7122fb2b3e10fc25d6a0d2242c6c93c0c1d98e8bd2dc4d8e8
3
+ size 17711656
ca40627786578d5d970628ea31bf6c71.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38b41728f1d85c755db309be099327fda70336835c9a29237fdaaacd02267a4
3
+ size 18872966
cf40301094ea1602d0e6dbcb86175f90.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13496b4bc5b89450519d88ad3e643c0694a4f606b2a81ff014d65384cfe73ef3
3
+ size 17370800
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.3-70B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 28672,
19
+ "inv_freq_config": {
20
+ "factor": 8.0,
21
+ "high_freq_factor": 4.0,
22
+ "low_freq_factor": 1.0,
23
+ "original_max_position_embeddings": 8192,
24
+ "rope_type": "llama3"
25
+ },
26
+ "max_position_embeddings": 131072,
27
+ "mlp_bias": false,
28
+ "model_type": "llama",
29
+ "num_attention_heads": 64,
30
+ "num_hidden_layers": 80,
31
+ "num_key_value_heads": 8,
32
+ "pretraining_tp": 1,
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 500000.0,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.48.1",
39
+ "use_cache": true,
40
+ "vocab_size": 128256
41
+ }
d34c4cdb4d23b46bfed727144031f8f1.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2770e878308433ad86875195ec03aa2f84c831868a1d15c0ebd1de6317b89458
3
+ size 30775926
d58b9a6bcdd4cb2029134bbc98ea5ac0.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46639963b8211d8bb56a37fb36d826e3df1cae0a4896a0c06ac708c67537788
3
+ size 30223878
d83e6614984530560e1f58d3926f6299.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638c1fabac1ea31834c320513125e3b79865b0e6640054cdae2ec98c42fc2eaf
3
+ size 4482192
dec1fe274c5d4eb04e7180793f4a4356.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d3c710e7c0ef26f8856cbf9887ac583d465693b32e8cf49a31f81243f585f3
3
+ size 31074953
ee35268bd794c72328a4e74610bdbee0.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63bf22497dbc494af31f50696d7f605b5267eaf15058de21cbcf782c5ccfac0c
3
+ size 31418375
f0300e102621d05ce20fa53c29d82aa5.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7376ee27e7e4456fa0180e9a651bd7c2458316b5729eb75d580b7cc2b22996
3
+ size 33288636
f0b27ab0212685b41bcf7a07a6a6333c.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23bb102480a91093dc1f884817e46af79852b14cdc61fde8fb33b5f7201d9d4
3
+ size 30269959
f11a4e51b9ea78e15ab75b3cd5ea91b2.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155e5e9fafe5167d88704987833226bfdd3209643c135d352fcd1ed4d825cb28
3
+ size 30770727
fa1734ff4313a29966f963dde2d9f6c5.edf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb6fcfe59c59c79fae80bbee6f9d17f7da1be04c2e9d7dcc2dd207a8b924a51
3
+ size 30128165
furiosa_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_version": "1.0.0",
3
+ "model_id": "meta-llama/Llama-3.3-70B-Instruct",
4
+ "model_kinds": [
5
+ "ARTIFACT"
6
+ ],
7
+ "model_class": {
8
+ "module": "furiosa_llm_models.llama3.symbolic.mlperf_submission",
9
+ "name": "LlamaForCausalLM"
10
+ },
11
+ "llm_config": {
12
+ "optimization_config": {
13
+ "attention_type": "PAGED_ATTENTION",
14
+ "optimize_rope": true,
15
+ "optimize_packed": true,
16
+ "decompose_layernorm": false,
17
+ "optimize_furiosa": false,
18
+ "use_unsplit_packed": false,
19
+ "compact_causal_mask": false,
20
+ "use_rngd_gelu": false,
21
+ "causal_mask_free_decoding": true,
22
+ "kv_cache_sharing_across_beams": false,
23
+ "inbound_beamsearch_softmax": false,
24
+ "calculate_logit_only_for_last_token": false,
25
+ "optimized_for_speculative_decoding": false,
26
+ "use_2d_masks": false,
27
+ "merged_kv_indices": false
28
+ },
29
+ "quantization_config": {
30
+ "weight": "bf16",
31
+ "activation": "bf16",
32
+ "kv_cache": "bf16",
33
+ "use_mcp": true
34
+ }
35
+ },
36
+ "components_versions": {
37
+ "furiosa_llm": {
38
+ "version": "0.1.0-dev",
39
+ "git_hash": "f285611",
40
+ "build_time": null
41
+ },
42
+ "furiosa_ir": {
43
+ "version": "0.11.0-dev",
44
+ "git_hash": "8c5160b804",
45
+ "build_time": "2025-07-30T04:23:32Z"
46
+ },
47
+ "furiosa_runtime": {
48
+ "version": "2025.3.0",
49
+ "git_hash": "834ab6188",
50
+ "build_time": "2025-07-30T04:27:48Z"
51
+ },
52
+ "furiosa_model_compressor": {
53
+ "version": "2025.3.0 (rev: 4cd9804)",
54
+ "git_hash": null,
55
+ "build_time": null
56
+ }
57
+ }
58
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }