Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
250
dacorvo HF staff commited on
Commit
4151b5d
•
1 Parent(s): f363ef5

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/ibm/labradorite-13b/cd69690e4daa0d46b110.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3659,3 +3659,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_ae5da897c251d6bd2a7b+2c2d707e/model.neff fi
3659
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e479f5c26e2db4cb80cd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3660
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f4b7cb5938042a42db61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3661
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fc04b57e26da18877508+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3659
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e479f5c26e2db4cb80cd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3660
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f4b7cb5938042a42db61+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3661
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fc04b57e26da18877508+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3662
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3663
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/ibm/labradorite-13b/cd69690e4daa0d46b110.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "end_token_id": 32000, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "ibm/labradorite-13b", "checkpoint_revision": "26921cf1d63c9c657e8260d08eaacc14fca43da0", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "pad_token_id": 32001, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32008}
neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0460a2b9681fa5a9a288219b9af7a221efc2632f4cde180bbdde968011fe7d43
3
+ size 542142
neuronxcc-2.14.227.0+2d4f85be/MODULE_67cbf19d01a91690bddf+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9625bbf0cd696a977d4b49917f8b6a624ebf15c42f1e1dff5847ae0e75a143d
3
+ size 6626304
neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18a691798510e965e609e298880a178bc86ecc219d6bba607483d528c3936a2a
3
+ size 420885
neuronxcc-2.14.227.0+2d4f85be/MODULE_bc0441f93668912f31f9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:159e1dea04bcd49311fd2e33ed24041b2a86ddb5530a83e30ccfb531c50f85a8
3
+ size 7117824