Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
200
dacorvo HF staff commited on
Commit
018afe9
•
1 Parent(s): 3aee24b

Synchronizing local compiler cache.

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 +22 -0
  2. neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+2c2d707e/model.neff +0 -0
  3. neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+9d134804/model.neff +0 -0
  4. neuronxcc-2.12.54.0+f631c2365/MODULE_1cbdc4423f554e2d26b9+2c2d707e/model.neff +0 -0
  5. neuronxcc-2.12.54.0+f631c2365/MODULE_20ebb867f689374d544b+2c2d707e/model.neff +0 -0
  6. neuronxcc-2.12.54.0+f631c2365/MODULE_25ae5b5e7cec711dafaa+2c2d707e/model.neff +0 -0
  7. neuronxcc-2.12.54.0+f631c2365/MODULE_34d558c33d28a2f62eeb+2c2d707e/model.neff +0 -0
  8. neuronxcc-2.12.54.0+f631c2365/MODULE_3a62ebe48e4d709dbe0a+2c2d707e/model.neff +0 -0
  9. neuronxcc-2.12.54.0+f631c2365/MODULE_4cb38fd1603a4aa3df3b+2c2d707e/model.neff +0 -0
  10. neuronxcc-2.12.54.0+f631c2365/MODULE_5b6baed10c9290668370+2c2d707e/model.neff +0 -0
  11. neuronxcc-2.12.54.0+f631c2365/MODULE_66169b8c3286d3b43293+2c2d707e/model.neff +0 -0
  12. neuronxcc-2.12.54.0+f631c2365/MODULE_7dd036b53c3737f19b01+2c2d707e/model.neff +0 -0
  13. neuronxcc-2.12.54.0+f631c2365/MODULE_8319c2aec2a3b0446fe1+2c2d707e/model.neff +0 -0
  14. neuronxcc-2.12.54.0+f631c2365/MODULE_a3e2249d29a748569a1e+2c2d707e/model.neff +0 -0
  15. neuronxcc-2.12.54.0+f631c2365/MODULE_a5117fb87fcc4e0ae0b1+2c2d707e/model.neff +0 -0
  16. neuronxcc-2.12.54.0+f631c2365/MODULE_bcdc114663caa637f97b+2c2d707e/model.neff +0 -0
  17. neuronxcc-2.12.54.0+f631c2365/MODULE_bd4e3797960f329f5d1a+2c2d707e/model.neff +0 -0
  18. neuronxcc-2.12.54.0+f631c2365/MODULE_da3eccfb2180e1a4f08a+2c2d707e/model.neff +0 -0
  19. neuronxcc-2.12.54.0+f631c2365/MODULE_e9cd6fe8779989fc400f+2c2d707e/model.neff +0 -0
  20. neuronxcc-2.12.54.0+f631c2365/MODULE_fa1974d8d211b3ce98a3+2c2d707e/model.neff +0 -0
  21. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/gpt2/gpt2/2081a5c9a30393646e54.json +1 -0
  22. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/gpt2/gpt2/3384c3f7f81ef00bc7b0.json +1 -0
  23. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-7b-chat-hf/a23bae888fd7fe3142b6.json +1 -0
  24. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-7b-chat-hf/a69cd10a7ef9072e186d.json +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/compile_flags.txt +1 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/model.hlo.pb +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/model.neff +3 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/compile_flags.txt +1 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/model.hlo.pb +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/model.neff +3 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/compile_flags.txt +1 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/model.hlo.pb +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/model.neff +3 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/compile_flags.txt +1 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/model.hlo.pb +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/model.neff +3 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/compile_flags.txt +1 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/model.hlo.pb +3 -0
  39. neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/model.neff +3 -0
  40. neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/compile_flags.txt +1 -0
  41. neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/model.hlo.pb +3 -0
  42. neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/model.neff +0 -0
  43. neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/compile_flags.txt +1 -0
  44. neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/model.hlo.pb +3 -0
  45. neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/model.neff +3 -0
  46. neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/compile_flags.txt +1 -0
  47. neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/model.hlo.pb +3 -0
  48. neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/model.neff +0 -0
  49. neuronxcc-2.12.68.0+4480452af/MODULE_5a88fb6d0bce38be72d4+2c2d707e/compile_flags.txt +1 -0
  50. neuronxcc-2.12.68.0+4480452af/MODULE_5a88fb6d0bce38be72d4+2c2d707e/model.hlo.pb +3 -0
.gitattributes CHANGED
@@ -866,3 +866,25 @@ neuronxcc-2.12.68.0+4480452af/MODULE_fd536f790fc50a1e7f18+2c2d707e/model.neff fi
866
  neuronxcc-2.12.68.0+4480452af/MODULE_fe2df69e856683d2f4f3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
867
  neuronxcc-2.12.68.0+4480452af/MODULE_fe6b7a34619145e26852+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
868
  neuronxcc-2.12.68.0+4480452af/MODULE_ff15a116fb592ccf7a7a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
866
  neuronxcc-2.12.68.0+4480452af/MODULE_fe2df69e856683d2f4f3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
867
  neuronxcc-2.12.68.0+4480452af/MODULE_fe6b7a34619145e26852+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
868
  neuronxcc-2.12.68.0+4480452af/MODULE_ff15a116fb592ccf7a7a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
869
+ neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
870
+ neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
871
+ neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
872
+ neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
873
+ neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
874
+ neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
875
+ neuronxcc-2.12.68.0+4480452af/MODULE_5a88fb6d0bce38be72d4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
876
+ neuronxcc-2.12.68.0+4480452af/MODULE_654dbdad1d3bf0617b84+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
877
+ neuronxcc-2.12.68.0+4480452af/MODULE_6e8a7da5b5492564315c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
878
+ neuronxcc-2.12.68.0+4480452af/MODULE_70d1a1ce4d52a869b9e6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
879
+ neuronxcc-2.12.68.0+4480452af/MODULE_99de89f709451a42193b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
880
+ neuronxcc-2.12.68.0+4480452af/MODULE_9e281341e7845ee2287f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
881
+ neuronxcc-2.12.68.0+4480452af/MODULE_a4faa198082ac5b8d787+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
882
+ neuronxcc-2.12.68.0+4480452af/MODULE_b9a15c837cee1bf59e24+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
883
+ neuronxcc-2.12.68.0+4480452af/MODULE_c46e110ea38cea049c6d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
884
+ neuronxcc-2.12.68.0+4480452af/MODULE_c7cd2842e8599931e798+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
885
+ neuronxcc-2.12.68.0+4480452af/MODULE_d0bb730ca21bad9031f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
886
+ neuronxcc-2.12.68.0+4480452af/MODULE_d0c07661be7193b513d8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
887
+ neuronxcc-2.12.68.0+4480452af/MODULE_d5006487226e226573ea+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
888
+ neuronxcc-2.12.68.0+4480452af/MODULE_d750f56f8d6a41f0372e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
889
+ neuronxcc-2.12.68.0+4480452af/MODULE_e22db4da23e4fde86dd1+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
890
+ neuronxcc-2.12.68.0+4480452af/MODULE_e57eb15cec4257484d35+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+9d134804/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+9d134804/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_051daf37f1af2e155915+9d134804/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_1cbdc4423f554e2d26b9+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_1cbdc4423f554e2d26b9+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_1cbdc4423f554e2d26b9+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_20ebb867f689374d544b+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_20ebb867f689374d544b+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_20ebb867f689374d544b+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_25ae5b5e7cec711dafaa+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_25ae5b5e7cec711dafaa+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_25ae5b5e7cec711dafaa+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_34d558c33d28a2f62eeb+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_34d558c33d28a2f62eeb+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_34d558c33d28a2f62eeb+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_3a62ebe48e4d709dbe0a+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_3a62ebe48e4d709dbe0a+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_3a62ebe48e4d709dbe0a+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_4cb38fd1603a4aa3df3b+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_4cb38fd1603a4aa3df3b+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_4cb38fd1603a4aa3df3b+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_5b6baed10c9290668370+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_5b6baed10c9290668370+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_5b6baed10c9290668370+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_66169b8c3286d3b43293+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_66169b8c3286d3b43293+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_66169b8c3286d3b43293+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_7dd036b53c3737f19b01+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_7dd036b53c3737f19b01+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_7dd036b53c3737f19b01+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_8319c2aec2a3b0446fe1+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_8319c2aec2a3b0446fe1+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_8319c2aec2a3b0446fe1+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_a3e2249d29a748569a1e+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_a3e2249d29a748569a1e+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_a3e2249d29a748569a1e+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_a5117fb87fcc4e0ae0b1+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_a5117fb87fcc4e0ae0b1+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_a5117fb87fcc4e0ae0b1+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_bcdc114663caa637f97b+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_bcdc114663caa637f97b+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_bcdc114663caa637f97b+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_bd4e3797960f329f5d1a+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_bd4e3797960f329f5d1a+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_bd4e3797960f329f5d1a+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_da3eccfb2180e1a4f08a+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_da3eccfb2180e1a4f08a+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_da3eccfb2180e1a4f08a+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_e9cd6fe8779989fc400f+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_e9cd6fe8779989fc400f+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_e9cd6fe8779989fc400f+2c2d707e/model.neff differ
 
neuronxcc-2.12.54.0+f631c2365/MODULE_fa1974d8d211b3ce98a3+2c2d707e/model.neff CHANGED
Binary files a/neuronxcc-2.12.54.0+f631c2365/MODULE_fa1974d8d211b3ce98a3+2c2d707e/model.neff and b/neuronxcc-2.12.54.0+f631c2365/MODULE_fa1974d8d211b3ce98a3+2c2d707e/model.neff differ
 
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/gpt2/gpt2/2081a5c9a30393646e54.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 50257, "n_positions": 1024, "n_embd": 768, "n_layer": 12, "n_head": 12, "n_inner": null, "activation_function": "gelu_new", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "architectures": ["GPT2LMHeadModel"], "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "model_type": "gpt2", "n_ctx": 1024, "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 2, "auto_cast_type": "fp32", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "gpt2", "checkpoint_revision": "11c5a3d5811f50298f278a704980280950aedb10"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/gpt2/gpt2/3384c3f7f81ef00bc7b0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 50257, "n_positions": 1024, "n_embd": 768, "n_layer": 12, "n_head": 12, "n_inner": null, "activation_function": "gelu_new", "resid_pdrop": 0.1, "embd_pdrop": 0.1, "attn_pdrop": 0.1, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "architectures": ["GPT2LMHeadModel"], "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "model_type": "gpt2", "n_ctx": 1024, "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp32", "sequence_length": 1024, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "gpt2", "checkpoint_revision": "11c5a3d5811f50298f278a704980280950aedb10"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-7b-chat-hf/a23bae888fd7fe3142b6.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.18/llama/meta-llama/Llama-2-7b-chat-hf/a69cd10a7ef9072e186d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd2d7d51abbc5fee2333ac101498b7325b437c226a546c0919dd284316af7f4c
3
+ size 131100
neuronxcc-2.12.68.0+4480452af/MODULE_1b5350910a1425db626c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f24238f83978fef8b7209f69c563f7eb2743eff84d8e54981dfd1926c6b7924
3
+ size 1117184
neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb198a13076d1853641fd0cabf393da5e7f171279762587df1b9ea082548851
3
+ size 297626
neuronxcc-2.12.68.0+4480452af/MODULE_1bf56f238691e0fd88c8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25f6911913ea26aebfc424db47991712b61cfa26e7a8d95fb59ad7de56f36556
3
+ size 12770304
neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37ede77a746b866b69da95ddc2504c4ea3155bed0c709b8566fa54ea1b2f8c6
3
+ size 300985
neuronxcc-2.12.68.0+4480452af/MODULE_1f6eaa498df4dc58af20+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a8262fa30782e5bcf46811cf3a5411bf3f1a3356986e8f711fcb893212c2b86
3
+ size 7998464
neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ff167f7293a2cd46df9112758109b2ac1016be8bb8340dc4ee1b346f465bfc7
3
+ size 298400
neuronxcc-2.12.68.0+4480452af/MODULE_22ea7dff3135b31f5101+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8d6e546fa8e23b7d284ee202cab293cf7ce973733701e83362e0f0678b26c0
3
+ size 13968384
neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1048195f697c5ce3577ce14f104f957ec1793ea7ec5de0312a8699e28a588a45
3
+ size 356822
neuronxcc-2.12.68.0+4480452af/MODULE_3a98b590a4918950bc9b+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f8719aeda5741024a46f47f67fc6312102614043cbdea4edda85779a0b3dc2
3
+ size 11398144
neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166bef555362d45dd5d023df1fe497c26fb7364722cbbd666977f3a8c4d6fd59
3
+ size 131100
neuronxcc-2.12.68.0+4480452af/MODULE_5086d2e4eb25478e5d07+2c2d707e/model.neff ADDED
Binary file (728 kB). View file
 
neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58697a9ee4977501158cc3ff941eb1deed3147c3657cff86d9bf7d8343697d6
3
+ size 298400
neuronxcc-2.12.68.0+4480452af/MODULE_514079ab36753b43b0d1+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f51b8256d25f41d21eeb3679713cdcf86d772282a52fb5f5bb776f66739544a
3
+ size 77118464
neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bef175a3c9be17abe04f786b92c337c006d3fdde0e55d9d2a26e516de73b49d
3
+ size 131100
neuronxcc-2.12.68.0+4480452af/MODULE_56467c9dfee3526c549a+2c2d707e/model.neff ADDED
Binary file (882 kB). View file
 
neuronxcc-2.12.68.0+4480452af/MODULE_5a88fb6d0bce38be72d4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5a88fb6d0bce38be72d4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7771318ac52eba9a801c8b5dbd8a21887ffd57842b00bbdb091e1bac12f154f8
3
+ size 295202