Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
180
dacorvo HF staff commited on
Commit
931773f
•
1 Parent(s): 221201f

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/01-ai/Yi-34B-200K/102403e8b14ba6cfddfc.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3703,3 +3703,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_d0b369b1faf22f574bf3+2c2d707e/model.neff fi
3703
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3704
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3705
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3703
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d4359d446aa8dcf57347+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3704
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f9f90a0e4915557c00e5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3705
  neuronxcc-2.14.227.0+2d4f85be/MODULE_ffd9059473e785125324+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3706
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3707
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/01-ai/Yi-34B-200K/102403e8b14ba6cfddfc.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, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "01-ai/Yi-34B-200K", "checkpoint_revision": "7c27c5cab0f5675edc0d9910769d0a6695ade7c7", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b48e06653b0b918fd5b861e67048ba302af5c9ef0b92639ec3700a54376238
3
+ size 678584
neuronxcc-2.14.227.0+2d4f85be/MODULE_01fa6588735031091399+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e999b77a439ee31556d30ec1aeec41786aac3af22809d1c1f5b88b09bd450c
3
+ size 7343104
neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af9b3306d25f686e27c7389c23935ecf391823f6fe6871744bfc2394e981c99
3
+ size 836829
neuronxcc-2.14.227.0+2d4f85be/MODULE_6e4acb26495819edaddf+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c766d1982599fa5c797c3c78f2f5927a61cf11d01eda959090628ec4ea575d
3
+ size 7732224