Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
dacorvo HF staff commited on
Commit
f1ca037
•
1 Parent(s): e1de034

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/gorilla-llm/gorilla-openfunctions-v2/17974dd7f23264e06557.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2110,3 +2110,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_f09c704459103a4c46d2+2c2d707e/model.neff fi
2110
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2111
  neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2112
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2110
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2111
  neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2112
  neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2113
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2114
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/gorilla-llm/gorilla-openfunctions-v2/17974dd7f23264e06557.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 100000, "eos_token_id": 100015, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "gorilla-llm/gorilla-openfunctions-v2", "checkpoint_revision": "0f91d705e64b77fb55e35a7eab5d03bf965c9b5c", "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": 30, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": false, "vocab_size": 102400}
neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27bef17d207f931c5413e16821e88f09008278b8098fa220fd84f7ad878b8a6
3
+ size 358294
neuronxcc-2.13.66.0+6dfecc895/MODULE_c71b4eab77289de33181+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3d1bb70704fe219a2688d23d33f38bf4eaba3fc633eb53a92d50a935a724869
3
+ size 15873024
neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9670875443ece5e926b133a7f3b20dc049b399ad52718f8ed6b9c5b51e3931d3
3
+ size 316084
neuronxcc-2.13.66.0+6dfecc895/MODULE_ddd26b7ff79df8739489+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c85e7e491219b607db8452e623e4f21a764eede994f26e9644195027def0fb7
3
+ size 16374784