Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
ecfc2ac
•
1 Parent(s): c91e7a6

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/mistralai/Mistral-7B-Instruct-v0.3/b75a8139f69c07162884.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3575,3 +3575,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_071ae1848f41f1fefe97+2c2d707e/model.neff fi
3575
  neuronxcc-2.14.227.0+2d4f85be/MODULE_714a09eb5c02060380ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3576
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7ea8729fe7ec338cc6bb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3577
  neuronxcc-2.14.227.0+2d4f85be/MODULE_896210e6c058c1a5341d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3575
  neuronxcc-2.14.227.0+2d4f85be/MODULE_714a09eb5c02060380ad+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3576
  neuronxcc-2.14.227.0+2d4f85be/MODULE_7ea8729fe7ec338cc6bb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3577
  neuronxcc-2.14.227.0+2d4f85be/MODULE_896210e6c058c1a5341d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3578
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3579
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/b75a8139f69c07162884.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": "fp16", "batch_size": 8, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "708a0609e640ac1edfb9020a7c934f51d34d6c79", "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, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06af5d376db7a67cbec8b3391ca9665347f993629a7231049863473b0edc8042
3
+ size 307162
neuronxcc-2.14.227.0+2d4f85be/MODULE_46bbf270b5b4ccbf10d5+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf742c93364e3d7e2511eab4c348d094af4c24984336d06662d49c240e0ddb9
3
+ size 30802944
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d128e0054b13cb85ce9d7fec1a71ca38201b1cd46cadfbbe0cc451aa3409512
3
+ size 360349
neuronxcc-2.14.227.0+2d4f85be/MODULE_8e6ce9261f2439a91508+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24868b31c77c49542fecf0652052f3be4e51291fd8bda8bebda20fc1f5ad351c
3
+ size 3267584