Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
204
dacorvo HF staff commited on
Commit
0f56f91
•
1 Parent(s): 33625bc

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/48083914077c2ad3f729.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1450,3 +1450,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_51ed3d04c1e4f84705a5+2c2d707e/model.neff fi
1450
  neuronxcc-2.12.68.0+4480452af/MODULE_c27051348450a336897e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1451
  neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1452
  neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1450
  neuronxcc-2.12.68.0+4480452af/MODULE_c27051348450a336897e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1451
  neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1452
  neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1453
+ neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1454
+ neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/48083914077c2ad3f729.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 64000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 48, "num_attention_heads": 32, "num_key_value_heads": 4, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 16, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "01-ai/Yi-9B", "checkpoint_revision": "58cdd0b4d4cdd2189bbf29a5773c73926084b753"}}
neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad7a9205e5fd4379e0e018adeb87a9467ec197cff550df39afdc71dea02bd66
3
+ size 592336
neuronxcc-2.12.68.0+4480452af/MODULE_b32452ccf9457b951e75+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c82c6283b5fed902e9b0438becf43ba6298441df25ce35289942a66e6286cd8
3
+ size 8295424
neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da7d9433412dd50249402c14dced02508983fd4eff13d40dd9b57dffd232290
3
+ size 525329
neuronxcc-2.12.68.0+4480452af/MODULE_cdde8380fd33b18e6b28+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de1a41b8d0fde012061451ef80ca32f62e314e4ec341b47ddb32f5fc9c83fbf
3
+ size 27720704