Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
philschmid HF staff commited on
Commit
0944c5c
•
1 Parent(s): ac34d64

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.54.0+f631c2365/0_REGISTRY/0.0.20.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/c6375c0f2bfb7e7adda8.json +1 -0
  3. neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1110,3 +1110,5 @@ neuronxcc-2.12.54.0+f631c2365/MODULE_cd65ba8843a32359ec00+2c2d707e/model.neff fi
1110
  neuronxcc-2.12.54.0+f631c2365/MODULE_db5539b50ebc5bcbbd60+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1111
  neuronxcc-2.12.54.0+f631c2365/MODULE_ed1f2cfc9ed8f94827ac+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1112
  neuronxcc-2.12.54.0+f631c2365/MODULE_fa6bf630231f5fa6370f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1110
  neuronxcc-2.12.54.0+f631c2365/MODULE_db5539b50ebc5bcbbd60+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1111
  neuronxcc-2.12.54.0+f631c2365/MODULE_ed1f2cfc9ed8f94827ac+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1112
  neuronxcc-2.12.54.0+f631c2365/MODULE_fa6bf630231f5fa6370f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1113
+ neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1114
+ neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.54.0+f631c2365/0_REGISTRY/0.0.20.dev0/inference/mistral/HuggingFaceH4/zephyr-7b-beta/c6375c0f2bfb7e7adda8.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "pad_token_id": 2, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 2, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.54.0+f631c2365", "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "b70e0c9a2d9e14bd1e812d3c398e5f313e93b473"}}
neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c31c9a1e6ed9e94db7c40d24c5afaa7a67443024189aae7fe28a1bb85c8c1102
3
+ size 134593327
neuronxcc-2.12.54.0+f631c2365/MODULE_66a5ceaf04d45256a16c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0caee32881b4537461ba46ad4d90e67408122d66fe638bc9f41097e449a94988
3
+ size 45272064
neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5b37e659fb53d1e80f57884cc76696611677dab789ab2c12c1297c8214996a
3
+ size 410520
neuronxcc-2.12.54.0+f631c2365/MODULE_c027baef6755d9b7c4ed+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500a8fff45a6f8723b60d356a035c4fcd063494ddbd8230f9afa4757828109aa
3
+ size 8991744