Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
1882217
•
1 Parent(s): 807070a

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/TencentARC/Mistral_Pro_8B_v0.1/88bda1b7f8de4ce0aab3.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3821,3 +3821,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_822353ab23bd7a754f0e+2c2d707e/model.neff fi
3821
  neuronxcc-2.14.227.0+2d4f85be/MODULE_979e2741e1191bbf9028+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3822
  neuronxcc-2.14.227.0+2d4f85be/MODULE_b1eab403668809dd1264+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3823
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fa043a5174a3eaaeac3d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3821
  neuronxcc-2.14.227.0+2d4f85be/MODULE_979e2741e1191bbf9028+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3822
  neuronxcc-2.14.227.0+2d4f85be/MODULE_b1eab403668809dd1264+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3823
  neuronxcc-2.14.227.0+2d4f85be/MODULE_fa043a5174a3eaaeac3d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3824
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3825
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/TencentARC/Mistral_Pro_8B_v0.1/88bda1b7f8de4ce0aab3.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": "2.14.227.0+2d4f85be", "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-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95f1b787579f7fe5fdb83b36537503322c169adda72129b66c5618a82b99fe4
3
+ size 671501502
neuronxcc-2.14.227.0+2d4f85be/MODULE_8ddfea458748cb6993a4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425b2c28372508cefdc13ca7bc675f21e40ad8bf0806d8f391609fa33e18c7a8
3
+ size 9769984
neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d8a0ac4915240614a852dbdca7723d11ce9eef19758c433e748de8c0745c2f
3
+ size 450429
neuronxcc-2.14.227.0+2d4f85be/MODULE_cbd0b6a150a6855048f6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a2e0ad069b3250c591ac774803dc088734f8f6ce14bac0baa8043fa55d4ecf
3
+ size 11244544