Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
629
dacorvo HF Staff commited on
Commit
1576b50
·
verified ·
1 Parent(s): f944ce2

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/qwen2/Qwen/Qwen2.5-0.5B/4ba9c6aa3d9f893cd139.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7275,3 +7275,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_2f5d0dadd623f2b18773+613edded/model.neff fi
7275
  neuronxcc-2.16.372.0+4a9b2326/MODULE_7aa4af831b941e1e7567+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7276
  neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7277
  neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7275
  neuronxcc-2.16.372.0+4a9b2326/MODULE_7aa4af831b941e1e7567+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7276
  neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7277
  neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7278
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7279
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/4ba9c6aa3d9f893cd139.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+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_81cb45fde7e941e6558d+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42daf944165bb8f0dc0d72bda95ca2a1fc9e0da80a7945d9d65a5828051a5454
3
+ size 302392
neuronxcc-2.16.372.0+4a9b2326/MODULE_81cb45fde7e941e6558d+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72cc9e7390cca4e7c75844abe7e130b79374eec894868b808457b4a0882ffcb5
3
+ size 1465344
neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+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_cb2d02d70e53cf8d12ae+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be9f30e4d32dee44d0c74df7f9da5db6c4d4fbcc5f0b476ac9926d99f0c3470
3
+ size 364340
neuronxcc-2.16.372.0+4a9b2326/MODULE_cb2d02d70e53cf8d12ae+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e4a554268222a78882879f13ccc77fb9f00020ad968084fdc1b6cd1c7f2b15b
3
+ size 17746944