dacorvo HF staff commited on
Commit
5d220aa
1 Parent(s): ab2d667

Synchronizing local compiler cache.

Browse files
Files changed (18) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/llama/NousResearch/Llama-2-7b-chat-hf/269c396ec83481c2a3e8.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/7fe3a7a1459e570afc30.json +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.neff +1 -1
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/compile_flags.txt +1 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/model.hlo_module.pb +3 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/model.neff +0 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.neff +1 -1
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/model.hlo_module.pb +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/model.neff +0 -0
  12. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/4864b759280870f8ca5c.json +1 -0
  13. neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/compile_flags.txt +1 -0
  14. neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/model.hlo_module.pb +3 -0
  15. neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/model.neff +3 -0
  16. neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/compile_flags.txt +1 -0
  17. neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/model.hlo_module.pb +3 -0
  18. neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3426,3 +3426,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_51c1595874507701efb3+2c2d707e/model.neff fi
3426
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3427
  neuronxcc-2.14.227.0+2d4f85be/MODULE_cf83f5b5494dc3bd20ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3428
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3426
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7c93371a4512559d9f77+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3427
  neuronxcc-2.14.227.0+2d4f85be/MODULE_cf83f5b5494dc3bd20ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3428
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f0d645907221fd556f37+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3429
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3430
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.23/inference/llama/NousResearch/Llama-2-7b-chat-hf/269c396ec83481c2a3e8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/7fe3a7a1459e570afc30.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 512, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_161d550e91fe728b06bd+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e395c4649375ec06276715f8aacd55629b62505883f9ac09ed61b0dcea5015
3
  size 20337664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:198f028517f4e4cdf4ed2b7a540beeeefb6de5e7f9d3d328a9473e91cd7902ec
3
  size 20337664
neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db64f3b8866b18de941294870a005b1375ed80c4b10a7f9ac675b83f9d9a3f58
3
+ size 54726
neuronxcc-2.13.66.0+6dfecc895/MODULE_66543a7926bc8232e535+2c2d707e/model.neff ADDED
Binary file (144 kB). View file
 
neuronxcc-2.13.66.0+6dfecc895/MODULE_af97e15eb5b056af300b+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c94aa286165b8f1d29d2f7912bf0fb2d31210403868e2205a11c2f7f2036af5b
3
  size 13200384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724b06c46dffda7a8b5a7318dd124989543d6f4b56a7a6bf418b5533025a2924
3
  size 13200384
neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fd59bb9c1882143d99aa051b203ae001fe9d186b69fc47e36bcbe4baa070dd
3
+ size 54726
neuronxcc-2.13.66.0+6dfecc895/MODULE_b13f20e9be1509d6af54+2c2d707e/model.neff ADDED
Binary file (155 kB). View file
 
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/meta-llama/Meta-Llama-3-8B/4864b759280870f8ca5c.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "62bd457b6fe961a42a631306577e622c83876cb6", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e52710d0b52260028a8196488cb834bcd2c033fc3d2504767be54c672a055ec
3
+ size 446150
neuronxcc-2.14.227.0+2d4f85be/MODULE_2ae933e12dd15d105c42+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395c3ef393f0dda27b0d771134eb07f8159fb2c3fea0723a62a9e96b0039f5b6
3
+ size 10271744
neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:278b0b37a4d36f41ef931fa1df5d39d935357caffdca3092bcc9eef37a892243
3
+ size 360718
neuronxcc-2.14.227.0+2d4f85be/MODULE_5721783cff00ee8bc640+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f551cb6c17162a0f3d032884e6fc62824d2628665d1eb116311aa94a1acc315
3
+ size 12811264