Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
202
dacorvo HF staff commited on
Commit
9f47359
•
1 Parent(s): afb189d

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/mistral/HuggingFaceH4/zephyr-7b-beta/45f7b47764407e08bc0d.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3759,3 +3759,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_e58de57b71035e2c2e9f+2c2d707e/model.neff fi
3759
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e775e935cc294b7618c2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3760
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6254d5ad0cf6b12d8321+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3761
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8071118b12745fc4d5ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3759
  neuronxcc-2.14.227.0+2d4f85be/MODULE_e775e935cc294b7618c2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3760
  neuronxcc-2.14.227.0+2d4f85be/MODULE_6254d5ad0cf6b12d8321+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3761
  neuronxcc-2.14.227.0+2d4f85be/MODULE_8071118b12745fc4d5ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3762
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3763
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/45f7b47764407e08bc0d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "b70e0c9a2d9e14bd1e812d3c398e5f313e93b473", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1c106be1a5d5fd386acf7aa75e4f29130f8c06a6984eb7939e407507672f4c
3
+ size 537201564
neuronxcc-2.14.227.0+2d4f85be/MODULE_a8f494756075b5f20b9e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059636d6e35a9259c1f2c5bc6f667f6a0142086bb456ddefc7ee3da3f8200611
3
+ size 32922624
neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ba1657cfca05630e59c9a51688203272b6bca78d04961bb4f194afab2cc0d7
3
+ size 360349
neuronxcc-2.14.227.0+2d4f85be/MODULE_f91b250a6e6128a5fd1a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37864b7d1a186fcb8983bc2f5fc8ffb96ef5f504e98c1df6e13dec8bddb4a8a0
3
+ size 3042304