Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
17cbb3e
•
1 Parent(s): 854eb44

Synchronizing local compiler cache.

Browse files
Files changed (14) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/01-ai/Yi-34B-200K/5b66966876b95b5064ff.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.neff +1 -1
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.neff +1 -1
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/compile_flags.txt +1 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.hlo.pb +3 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.neff +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.neff +1 -1
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.neff +1 -1
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.neff +1 -1
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.neff +1 -1
.gitattributes CHANGED
@@ -2180,3 +2180,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_a46508abda15be3d59d5+2c2d707e/model.neff fi
2180
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d3c9158bddf0842033ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2181
  neuronxcc-2.13.66.0+6dfecc895/MODULE_da61ba5a3e15c764428a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc5d572670bf11c06b07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2180
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d3c9158bddf0842033ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2181
  neuronxcc-2.13.66.0+6dfecc895/MODULE_da61ba5a3e15c764428a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2182
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc5d572670bf11c06b07+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2183
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2184
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/01-ai/Yi-34B-200K/5b66966876b95b5064ff.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": 7168, "initializer_range": 0.02, "intermediate_size": 20480, "max_position_embeddings": 200000, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "01-ai/Yi-34B-200K", "checkpoint_revision": "4277a28017f0e631526d3a59d50dfcd3f583fb30", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 56, "num_hidden_layers": 60, "num_key_value_heads": 8, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 64000}
neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcbe2daf0bd1523eaf6773922a92cec7705e9f723a0bf9817dbc72eda75cbc3
3
+ size 719984
neuronxcc-2.13.66.0+6dfecc895/MODULE_3a4f8d0ddbe39cd52669+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5145ea3fa470c89986b945d8bbbe5c736f46fead2a3c5cfc50f01bc8686b9622
3
+ size 8530944
neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf78c85ab7806cc2075ff607e2b006d2191297606973107073641b32c6804b2
3
  size 9606144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29dfd77ed3670a75c09a7c3c6987384b80785b32af1444a41ac687501836fee7
3
  size 9606144
neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e100a1f39124851ac66beac14774e9e19f6ae128b83cc2bf8f35193f188b07c
3
  size 10497024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfbcac10c4cc4366e2acb0582265a278b738a69d6a0462aab3b70ef62cef1bb
3
  size 10497024
neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b004bbf10da12d48180c1175bef086f8b28ad3973a6d413324f2e89025c4601
3
+ size 634587
neuronxcc-2.13.66.0+6dfecc895/MODULE_b4af342f92f46fba85a3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfbddca3f24964e653b907ca87da9382ddb8af46d4c072807a652845a7c6590
3
+ size 5868544
neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eea54fc3b8391c171d440a67d4d3548f522b54dfa767c512aaca55510a8f4dd9
3
  size 15770624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b9ea1c0b50b7da5b2aa11c351b050f1f8f52b9f060ece18091cdf7545aa617
3
  size 15770624
neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a210ffa48a264bd7529b9ab102872f51e67833c6186d62f429bedbbda3a216
3
  size 27331584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2183834c28e845c2f089587c357faae4dcbe7bbb9e73aa7181d08480073ca65
3
  size 27331584
neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2167d688a780bac598db04036504f66f6102e6b551376f823abfdddb64719bfa
3
  size 27331584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4ca88311b46db7fb08764b296172b083357e0f90d6a308f0beddeabbefc771
3
  size 27331584
neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52a119fe64ae5207b13f02f8577981b31a9e516b708f6297fe8da717eb31797f
3
  size 18596864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f777b54ba05cbaf3ce1babce3c20bc2c2388aeec0bb4867bcf98f1a3478657c
3
  size 18596864