Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
86f51f0
·
verified ·
1 Parent(s): eb6e10a

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/mistralai/Mistral-Small-Instruct-2409/327da1f834b63f54e5c8.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7232,3 +7232,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_5d5e4206a466b7852561+613edded/model.neff fi
7232
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7233
  neuronxcc-2.16.372.0+4a9b2326/MODULE_39cb90b37ee6fff24f5d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7234
  neuronxcc-2.16.372.0+4a9b2326/MODULE_45dec79bcb55d7eacd60+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7232
  neuronxcc-2.16.372.0+4a9b2326/MODULE_b5092ae1e071cef3fe8a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7233
  neuronxcc-2.16.372.0+4a9b2326/MODULE_39cb90b37ee6fff24f5d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7234
  neuronxcc-2.16.372.0+4a9b2326/MODULE_45dec79bcb55d7eacd60+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7235
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7236
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/mistralai/Mistral-Small-Instruct-2409/327da1f834b63f54e5c8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "initializer_range": 0.02, "intermediate_size": 16384, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "mistralai/Mistral-Small-Instruct-2409", "checkpoint_revision": "8012044390bdc1c6d8ab162f5416220f43bf517b", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 12, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 48, "num_hidden_layers": 56, "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-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bf22268e7fef54a6c38193126038c989c575047896736caad701fc803abefd
3
+ size 507621
neuronxcc-2.16.372.0+4a9b2326/MODULE_58b2a0d4bcc7c70ab5b0+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e2694f3a33ac20939ccfefe22cd02b4230102ae7ea71621eff337d16ca0930
3
+ size 2704384
neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd142c9ba1e1a1969ea5d9a4f65d4fae81ae86956c7c2617294e2f89edbcf09
3
+ size 594303
neuronxcc-2.16.372.0+4a9b2326/MODULE_d940b43da508034d0efd+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d787a38aa0dd72b9855c9595e0c9bdb668866239cfa87f9eb21c8373427b591d
3
+ size 7486464