Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
276
dacorvo HF staff commited on
Commit
492a248
•
1 Parent(s): 485e40c

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/fc21fbc979e817ced360.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3617,3 +3617,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_d2279c331e8ffefbc7e4+2c2d707e/model.neff fi
3617
  neuronxcc-2.14.227.0+2d4f85be/MODULE_dff82c69deb8f0687340+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3618
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eb60c8242671b90f0628+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3619
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1e061138c1478ad3518+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3617
  neuronxcc-2.14.227.0+2d4f85be/MODULE_dff82c69deb8f0687340+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3618
  neuronxcc-2.14.227.0+2d4f85be/MODULE_eb60c8242671b90f0628+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3619
  neuronxcc-2.14.227.0+2d4f85be/MODULE_f1e061138c1478ad3518+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3620
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3621
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/llama/princeton-nlp/Sheared-LLaMA-1.3B/fc21fbc979e817ced360.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5504, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "princeton-nlp/Sheared-LLaMA-1.3B", "checkpoint_revision": "a4b76938edbf571ea7d7d9904861cbdca08809b4", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7a1f64775194b197a43a8bdb70ff28b09a10f99ff1bda0a925e15d70f9db591
3
+ size 325402
neuronxcc-2.14.227.0+2d4f85be/MODULE_3f2eaabf2b2557180030+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e334e3733b743a563d77a17e459fd7d663b7888d23f2a512dfb673e1428827
3
+ size 28969984
neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b259e107b3c9dbca16a6d5cc554b1629ef64b2b250a985f8b12d77042303ff3
3
+ size 252498
neuronxcc-2.14.227.0+2d4f85be/MODULE_b56a2aeda0f893ae933e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9ed1bec2d20748cbd0106087609366e4feb454bd777788c6af2b0ea680bef5
3
+ size 3841024