Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
183
dacorvo HF staff commited on
Commit
e1de034
•
1 Parent(s): de886c9

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/ibm/merlinite-7b/6881843f1816229bace0.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2108,3 +2108,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_b3a23c217a7cf8484b60+2c2d707e/model.neff fi
2108
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b83cfc30dfa5bb3ba761+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2109
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f09c704459103a4c46d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2110
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2108
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b83cfc30dfa5bb3ba761+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2109
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f09c704459103a4c46d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2110
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2111
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2112
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/mistral/ibm/merlinite-7b/6881843f1816229bace0.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "end_token_id": 32000, "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": "ibm/merlinite-7b", "checkpoint_revision": "233d12759d5bb9344231dafdb51310ec19d79c0e", "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": 32, "num_key_value_heads": 8, "pad_token_id": 32001, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32008}
neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79b942e1d917aecf7b8f6e939d45ec0cef2f6dd904f7f7547716cb0f495f25d
3
+ size 537236624
neuronxcc-2.13.66.0+6dfecc895/MODULE_6f53befbe8a9ee401d50+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f028f2c9f3ceba55c0aa018d860839df2a946c2141dec881008fec05069a2c
3
+ size 13896704
neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd03173fee61611875cd300e1b65d3d53cc7a5e9e935d7e333ed9a9a8179e38
3
+ size 399032
neuronxcc-2.13.66.0+6dfecc895/MODULE_a465983b970242364d05+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309d28d9f7c07ec023e5b24b5ab742d55d57c7a213b63c1648648624c3b2ed87
3
+ size 10589184