Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
f944ce2
·
verified ·
1 Parent(s): ec7f889

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/f1fe8d4a65a4614a665a.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7273,3 +7273,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_decoder/model.neur
7273
  neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
7274
  neuronxcc-2.16.372.0+4a9b2326/MODULE_2f5d0dadd623f2b18773+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
 
 
 
7273
  neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
7274
  neuronxcc-2.16.372.0+4a9b2326/MODULE_2f5d0dadd623f2b18773+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
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/f1fe8d4a65a4614a665a.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": 1, "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_08e3d3755d9db0fe195a+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_08e3d3755d9db0fe195a+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12c8e43acef9aa527b6d216d9dfe23dd0a85cbf76e06bac2deec585b506c6fdc
3
+ size 278717
neuronxcc-2.16.372.0+4a9b2326/MODULE_08e3d3755d9db0fe195a+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab09f0589edb9a265ff53643fc2e8de210b669092d3c2f284e46e9ab7ddef2ea
3
+ size 1004544
neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+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_df527b17f4dcc2f89825+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9a28ae710d1efb0438cf5038cf19d491cb4e1a275128e6e27f3e03b1434ca4
3
+ size 330244
neuronxcc-2.16.372.0+4a9b2326/MODULE_df527b17f4dcc2f89825+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb0b85f45053be12ea66efbf8c41c1757287b25b54c01d783d523f331c0e4b1
3
+ size 18013184