Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
50d2c5b
·
verified ·
1 Parent(s): 4674095

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/HuggingFaceH4/zephyr-7b-beta/bce0bf86a51ac631df0a.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7141,3 +7141,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_45ba236fea2f4d3185e5+613edded/model.neff fi
7141
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7142
  neuronxcc-2.16.372.0+4a9b2326/MODULE_01a4748c99030fe69987+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7143
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7141
  neuronxcc-2.16.372.0+4a9b2326/MODULE_d19a1e232b685790492d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7142
  neuronxcc-2.16.372.0+4a9b2326/MODULE_01a4748c99030fe69987+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7143
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7144
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7145
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/HuggingFaceH4/zephyr-7b-beta/bce0bf86a51ac631df0a.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": 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": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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": 2, "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-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+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_52f77cf05a48696d505f+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa64e2242882ebae41eba74c882325cb659c171fa0b7be8d757340cc5ce9cc41
3
+ size 363541
neuronxcc-2.16.372.0+4a9b2326/MODULE_52f77cf05a48696d505f+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9741cb0bc6cac71c236425b42446488e6277214c6bcb29aa2154984bd5a157c2
3
+ size 8735744
neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+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_7e8a971b679cd1f1877b+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d0b26290611750475222ffe3d4af958525a29574c9be47a3f92b6e3fb8168c
3
+ size 537196468
neuronxcc-2.16.372.0+4a9b2326/MODULE_7e8a971b679cd1f1877b+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb8481e496248ed6519d78fd8224baa2d0e117f6eaf19cf78f719aecdbfaea8
3
+ size 6452224