Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
239
dacorvo HF staff commited on
Commit
f8cbd65
•
1 Parent(s): 7e577ee

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-2-7b-chat-hf/bcfe2af7039d2c9700a4.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1633,3 +1633,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_2fa05f5ec5572932877c+2c2d707e/model.neff fi
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
 
 
 
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
1636
+ neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1637
+ neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+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-2-7b-chat-hf/bcfe2af7039d2c9700a4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "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": 32, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33"}}
neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e621e1056bef42f81467d52ea5634bbfe49d7fff205209ec3063cdd31fb5ea7
3
+ size 395290
neuronxcc-2.12.68.0+4480452af/MODULE_d8a7644bdc06e7d648dc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f269199c66e2418be77a19ef20c90798ce377ea5ee9cc0449acebfd0555e8a
3
+ size 10497024
neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1242c8a89a3199e0c56b3de066bc4b699f77a49b789f586afab2c9fbc6725144
3
+ size 350447
neuronxcc-2.12.68.0+4480452af/MODULE_db2467569399722e7d82+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7935a1ed89cbc20c8af6d9820cb628fd1737edd2c5d4e845fcc1809268779b93
3
+ size 18637824