Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
204
dacorvo HF staff commited on
Commit
cc04302
•
1 Parent(s): 1404080

Synchronizing local compiler cache.

Browse files
Files changed (15) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/8aa960d3bb25ee6a1ecc.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.log +1 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.neff +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/compile_flags.txt +1 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/model.hlo.pb +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1439,3 +1439,6 @@ neuronxcc-2.12.68.0+4480452af/MODULE_a1dda003133e2eace842+2c2d707e/model.neff fi
1439
  neuronxcc-2.12.68.0+4480452af/MODULE_ae5979a76b292f9d4c98+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1440
  neuronxcc-2.12.68.0+4480452af/MODULE_cdf838d730573aa6962d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1441
  neuronxcc-2.12.68.0+4480452af/MODULE_d13eb1187f0f4617dd99+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
1439
  neuronxcc-2.12.68.0+4480452af/MODULE_ae5979a76b292f9d4c98+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1440
  neuronxcc-2.12.68.0+4480452af/MODULE_cdf838d730573aa6962d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1441
  neuronxcc-2.12.68.0+4480452af/MODULE_d13eb1187f0f4617dd99+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1442
+ neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1443
+ neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1444
+ neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/8aa960d3bb25ee6a1ecc.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 64000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 48, "num_attention_heads": 32, "num_key_value_heads": 4, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "01-ai/Yi-9B", "checkpoint_revision": "58cdd0b4d4cdd2189bbf29a5773c73926084b753"}}
neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a73e17df8f01552b8f29d33c116778f14fa306df4e68aec8b1dacad638bc960
3
+ size 523793
neuronxcc-2.12.68.0+4480452af/MODULE_3218b82488e46c72e8d3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99a89e12088d5c0b04e8863dcf3c4768a75591010fd67c89f65bbcbfec547e3c
3
+ size 44944384
neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64ba3acd84dedd6e7baa9d6eb4248d4605516d11890b9a06494915a433930cfd
3
+ size 615961
neuronxcc-2.12.68.0+4480452af/MODULE_4925efd8b2ff655a2bc9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ddc99620d307dec6ac5f9f469a2e8d55edd1a7b025b1b2097a3505c54c6a94
3
+ size 14388224
neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c63b9ebb24dd87e5ffdaa15248bee31f7f90e21461ff3675085e60eb2931c9
3
+ size 535995
neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.log ADDED
@@ -0,0 +1 @@
 
 
1
+ Failed compilation with ['neuronx-cc', '--target=trn1', 'compile', '--framework', 'XLA', '/tmp/ubuntu/neuroncc_compile_workdir/f54254ad-9707-4ad2-81d4-537d11fe89e7/model.MODULE_a162fd51beecfdd0d4a8+2c2d707e.hlo.pb', '--output', '/tmp/ubuntu/neuroncc_compile_workdir/f54254ad-9707-4ad2-81d4-537d11fe89e7/model.MODULE_a162fd51beecfdd0d4a8+2c2d707e.neff', '--model-type=transformer', '--auto-cast=none', '--verbose=35']: 2024-03-20T18:51:05Z [LUR015] Compiler generated too many instructions (5293923). This maybe due to a failure in parallelism extraction by the tensorizer. - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new
neuronxcc-2.12.68.0+4480452af/MODULE_a162fd51beecfdd0d4a8+2c2d707e/model.neff ADDED
@@ -0,0 +1 @@
 
 
1
+ ERROR
neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2a60c2737c8809d75aa5108dc5d6ceb4412513ab01b51c57e5600c84744082
3
+ size 590800
neuronxcc-2.12.68.0+4480452af/MODULE_b10ece217e6a32d58329+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f90b9b76b250b5dc4e27c2d8db5575d7e45ce23e7399612c79c48a0b66921b56
3
+ size 6697984