Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
242
dacorvo HF staff commited on
Commit
33625bc
•
1 Parent(s): 9a2eff0

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/70383789a8476a70f3d6.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1448,3 +1448,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_ccde39f97b9743642a71+2c2d707e/model.neff fi
1448
  neuronxcc-2.12.68.0+4480452af/MODULE_df230a1fe5e7c0de8010+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1449
  neuronxcc-2.12.68.0+4480452af/MODULE_51ed3d04c1e4f84705a5+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
 
 
 
1448
  neuronxcc-2.12.68.0+4480452af/MODULE_df230a1fe5e7c0de8010+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1449
  neuronxcc-2.12.68.0+4480452af/MODULE_51ed3d04c1e4f84705a5+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
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/01-ai/Yi-9B/70383789a8476a70f3d6.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": 8, "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_7ff07acc6aab2752d697+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d14817ebfea5274147fc3c3128be49401fd4b59297db19397ce53adc8c3c5b
3
+ size 523793
neuronxcc-2.12.68.0+4480452af/MODULE_7ff07acc6aab2752d697+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32650001c2c23c2ccc905c51ad6a3fbd14295214b0e92e92baf3f0f3b970c86a
3
+ size 44882944
neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ffacec62cb636ba20fad14845b16668552c8f5836447e842dd9135a0e7bd6ad
3
+ size 590800
neuronxcc-2.12.68.0+4480452af/MODULE_973b8d44b83c3068d7c4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6e9e320e5bf99671dab5ba62a6c7854d507482054cceedbc5bb2978c14120f
3
+ size 14244864