Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
50f16a0
•
1 Parent(s): 25936b5

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/ibm/labradorite-13b/de590b276603d3e9c4fc.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1504,3 +1504,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.neff fi
1504
  neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1505
  neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1506
  neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1504
  neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1505
  neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1506
  neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1507
+ neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1508
+ neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/ibm/labradorite-13b/de590b276603d3e9c4fc.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32008, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "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": 32001, "eos_token_id": 2, "end_token_id": 32000, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "ibm/labradorite-13b", "checkpoint_revision": "26921cf1d63c9c657e8260d08eaacc14fca43da0"}}
neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da377a9f5746e031ea44c3aefd23e0b4dc5aa56db2c1cc543bdb1a7578541b36
3
+ size 436608
neuronxcc-2.12.68.0+4480452af/MODULE_5d8e70b03df21d2287f8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a390ed73d5ed47f6ef4bb5eaa23bb977c4d56df78be4df96aa64d908db0fe569
3
+ size 56157184
neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4ee652c928076068fe7c1b6e59f8fa1d1849856f8bcccf4f262ad3ba611cfe
3
+ size 492467
neuronxcc-2.12.68.0+4480452af/MODULE_f2cf83bca83ca88b75fc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6863a68a4f66b4f13eb6f02c93fda1819600d1c6ddb4d604f3afb17cc07f3280
3
+ size 7947264