Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
6392789
•
1 Parent(s): 328c92d

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/0e72b5096b0335d9a9ce.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1631,3 +1631,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff fi
1631
  neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1632
  neuronxcc-2.12.68.0+4480452af/MODULE_2fa05f5ec5572932877c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1633
  neuronxcc-2.12.68.0+4480452af/MODULE_7a81cc986c7c4a08fb91+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1631
  neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1632
  neuronxcc-2.12.68.0+4480452af/MODULE_2fa05f5ec5572932877c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1633
  neuronxcc-2.12.68.0+4480452af/MODULE_7a81cc986c7c4a08fb91+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1634
+ neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1635
+ neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-13b-chat-hf/0e72b5096b0335d9a9ce.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "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": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "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": "meta-llama/Llama-2-13b-chat-hf", "checkpoint_revision": "29655417e51232f4f2b9b5d3e1418e5a9b04e80e"}}
neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:825115b415b1c6a2e51bea1392a723ebff3ec49a322343403991713e1475c768
3
+ size 492467
neuronxcc-2.12.68.0+4480452af/MODULE_969c17164a31587478b2+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b52c68d1a9778495935231a95652698a8a3d938d2a72aa6258b1e79c180da9b
3
+ size 16200704
neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c05fd59d24007f2e20fd934864ab520e13da4f1eec1f98ddaa56071a96082ce
3
+ size 436608
neuronxcc-2.12.68.0+4480452af/MODULE_f5a8bac0be3e151e7221+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4536c63543660becda5f3d283dd82e64b72134946e0d391dba605f3623d0d516
3
+ size 56177664