Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
236
dacorvo HF staff commited on
Commit
16dd05a
•
1 Parent(s): eac9131

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/mistral/TencentARC/Mistral_Pro_8B_v0.1/1355ddd342dd3f226fbf.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2152,3 +2152,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff fi
2152
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb697231bd571222e516+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2153
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ca5d84581f54d4419a0b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2154
  neuronxcc-2.13.66.0+6dfecc895/MODULE_cb6fe28fbef826b27c49+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2152
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb697231bd571222e516+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2153
  neuronxcc-2.13.66.0+6dfecc895/MODULE_ca5d84581f54d4419a0b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2154
  neuronxcc-2.13.66.0+6dfecc895/MODULE_cb6fe28fbef826b27c49+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2155
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2156
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/mistral/TencentARC/Mistral_Pro_8B_v0.1/1355ddd342dd3f226fbf.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": "TencentARC/Mistral_Pro_8B_v0.1", "checkpoint_revision": "366f159fc5b314ba2a955209d2bca4600f84dac0", "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": 40, "num_key_value_heads": 8, "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-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789b06b8c985ac60b6ed4f38bc083bab2ddd7675d8a3209b56154dff68d1cd74
3
+ size 671545592
neuronxcc-2.13.66.0+6dfecc895/MODULE_1e8067db91f5ad8c7f97+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662ba3093f0bc01704a7da47a5016051455b9edbaba910d2ac8e621481dfd82b
3
+ size 14459904
neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b75dd677e5bd3f575ebf00a1b080acdbccf479ff3b029e63522d9bd17ba81c1
3
+ size 498410
neuronxcc-2.13.66.0+6dfecc895/MODULE_321e95d123675fdc3d36+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8299022af02d232a7cabba62eb3933db11a88257f04312a9578b67cf270c6bb
3
+ size 13097984