Hugging Face's logo

aws-neuron
/
Qwen3-8BSharded

Model card Files
xet
Community
jburtoft commited on
Commit
9725092
·
verified ·
1 Parent(s): ee61cf7

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +8 -0
  2. context_encoding_model/_tp0_bk0/model/graph.hlo +3 -0
  3. context_encoding_model/_tp0_bk0/neuron_config.json +1 -1
  4. context_encoding_model/_tp0_bk1/model/graph.hlo +3 -0
  5. context_encoding_model/_tp0_bk1/neuron_config.json +1 -1
  6. context_encoding_model/_tp0_bk2/model/graph.hlo +3 -0
  7. context_encoding_model/_tp0_bk2/neuron_config.json +1 -1
  8. context_encoding_model/_tp0_bk3/model/graph.hlo +3 -0
  9. context_encoding_model/_tp0_bk3/neuron_config.json +1 -1
  10. layout_opt/graph.neff +1 -1
  11. layout_opt/log-neuron-cc.txt +0 -0
  12. model.pt +1 -1
  13. neuron_config.json +1 -1
  14. token_generation_model/_tp0_bk0/model/graph.hlo +3 -0
  15. token_generation_model/_tp0_bk0/neuron_config.json +1 -1
  16. token_generation_model/_tp0_bk1/model/graph.hlo +3 -0
  17. token_generation_model/_tp0_bk1/neuron_config.json +1 -1
  18. token_generation_model/_tp0_bk2/model/graph.hlo +3 -0
  19. token_generation_model/_tp0_bk2/neuron_config.json +1 -1
  20. token_generation_model/_tp0_bk3/model/graph.hlo +3 -0
  21. token_generation_model/_tp0_bk3/neuron_config.json +1 -1
  22. weights/tp0_sharded_checkpoint.safetensors +2 -2
  23. weights/tp1_sharded_checkpoint.safetensors +2 -2
.gitattributes CHANGED
@@ -38,3 +38,11 @@ token_generation_model/_tp0_bk3/graph.neff filter=lfs diff=lfs merge=lfs -text
38
  token_generation_model/_tp0_bk3/metaneff.pb filter=lfs diff=lfs merge=lfs -text
39
  token_generation_model/_tp0_bk3/model.MODULE_d3ed4857bd8baeff8023+b05cff0a.hlo_module.pb filter=lfs diff=lfs merge=lfs -text
40
  token_generation_model/_tp0_bk3/model.MODULE_d3ed4857bd8baeff8023+b05cff0a.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
38
  token_generation_model/_tp0_bk3/metaneff.pb filter=lfs diff=lfs merge=lfs -text
39
  token_generation_model/_tp0_bk3/model.MODULE_d3ed4857bd8baeff8023+b05cff0a.hlo_module.pb filter=lfs diff=lfs merge=lfs -text
40
  token_generation_model/_tp0_bk3/model.MODULE_d3ed4857bd8baeff8023+b05cff0a.neff filter=lfs diff=lfs merge=lfs -text
41
+ context_encoding_model/_tp0_bk0/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
42
+ context_encoding_model/_tp0_bk1/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
43
+ context_encoding_model/_tp0_bk2/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
44
+ context_encoding_model/_tp0_bk3/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
45
+ token_generation_model/_tp0_bk0/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
46
+ token_generation_model/_tp0_bk1/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
47
+ token_generation_model/_tp0_bk2/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
48
+ token_generation_model/_tp0_bk3/model/graph.hlo filter=lfs diff=lfs merge=lfs -text
context_encoding_model/_tp0_bk0/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89b9e073981a0b1b7d0bbd0a24f147e9df13c5706d9d6be9971b857124c9496
3
+ size 1119812
context_encoding_model/_tp0_bk0/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
context_encoding_model/_tp0_bk1/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03debb723d63387ea26771f63729d616ac71a0dbfcb78d21d2194ff723fcbc1
3
+ size 1229637
context_encoding_model/_tp0_bk1/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
context_encoding_model/_tp0_bk2/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970c5138d61d773fc00bacb9090fbc05a05573925b8d91068006c211596d3f78
3
+ size 1450821
context_encoding_model/_tp0_bk2/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
context_encoding_model/_tp0_bk3/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9068f3ba4f55e1b8b35adde74efc6a9e617baa344783aaee62353f9181c3092c
3
+ size 1893189
context_encoding_model/_tp0_bk3/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
layout_opt/graph.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eafae43287bda2aa58740df223d211d8e3638af29e402c9cc6cbcadcf302ddde
3
  size 5786624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c99aedcf56baf5659b3ff9ace3614db4a41187ffd5086ca55949f07834f10b
3
  size 5786624
layout_opt/log-neuron-cc.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c36077018a9f85728962cc73bfcba755ce1d5d5b6f608dacf65d7b95596eb109
3
  size 47198475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521012db0970cf3545627c393965ac44720fab6a173fd09081e35e4ce0e6128e
3
  size 47198475
neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
token_generation_model/_tp0_bk0/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b84de1c7109b93d3bf677f50a6adfce9d88aab86c7f512a7234c08cd856732f
3
+ size 957497
token_generation_model/_tp0_bk0/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
token_generation_model/_tp0_bk1/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c565989bf644de18fb8b4dbcf5ae03d0be2bfe8bc7c9308e7954d0a9db691fc
3
+ size 1063359
token_generation_model/_tp0_bk1/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
token_generation_model/_tp0_bk2/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c544d0e20f56d5383d37218086cb993108067db2d992950c04a8fb8d9b4a59b
3
+ size 1063359
token_generation_model/_tp0_bk2/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
token_generation_model/_tp0_bk3/model/graph.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:632099279834ad49336b20fe638b015f3bd9f3d5379c77ef3a7fbaef8cea450e
3
+ size 1063359
token_generation_model/_tp0_bk3/neuron_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_attn_implementation_autoset": false,
3
- "_name_or_path": "Qwen/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
 
1
  {
2
  "_attn_implementation_autoset": false,
3
+ "_name_or_path": "/home/ubuntu/models/Qwen3-8B",
4
  "add_cross_attention": false,
5
  "architectures": [
6
  "Qwen3ForCausalLM"
weights/tp0_sharded_checkpoint.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4877d7d89bdfdd5be52c247b3b385259dc7ec681b73afe86869d1c63a818d966
3
- size 135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15341a7fe906f9d9252627ff9c81c2ed50e868ea3dacec64d4193b96a1048be2
3
+ size 8191092036
weights/tp1_sharded_checkpoint.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b199546177db3fbfff12b306890012363eaef2e0c65937c1fa18a4135541fa64
3
- size 135
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ae410f8ce85333f4fcbf1b559f08849fde48ce9a9a17f645822ace61002789
3
+ size 8191092036