Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
philschmid HF staff commited on
Commit
c813817
•
1 Parent(s): 944d15b

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.54.0+f631c2365/0_REGISTRY/0.0.20.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/30f1cf39d363d3413d58.json +1 -0
  3. neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1117,3 +1117,5 @@ neuronxcc-2.12.54.0+f631c2365/MODULE_9213147f5b6ee8ba982f+2c2d707e/model.neff fi
1117
  neuronxcc-2.12.54.0+f631c2365/MODULE_101d6badbbc22d979db6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1118
  neuronxcc-2.12.54.0+f631c2365/MODULE_96c74602c6595c924750+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1119
  neuronxcc-2.12.54.0+f631c2365/MODULE_b731fc0c29ae932dea47+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1117
  neuronxcc-2.12.54.0+f631c2365/MODULE_101d6badbbc22d979db6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1118
  neuronxcc-2.12.54.0+f631c2365/MODULE_96c74602c6595c924750+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1119
  neuronxcc-2.12.54.0+f631c2365/MODULE_b731fc0c29ae932dea47+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1120
+ neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1121
+ neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.54.0+f631c2365/0_REGISTRY/0.0.20.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/30f1cf39d363d3413d58.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": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.54.0+f631c2365", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}}
neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65e10acdd5186bd49cc88f6ceed76bc84748ee6f076de343193b6be4534c210
3
+ size 297626
neuronxcc-2.12.54.0+f631c2365/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9813ca9ed6bf6c9f3d3a48b3fc0e4b905838ee1457ef6bc3b024bb953070e5ec
3
+ size 47197184
neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcd5ec203680dc9542cd1844a28f544e8c6ac9d72b4a94498c04cf285a93d59
3
+ size 300985
neuronxcc-2.12.54.0+f631c2365/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74002cc407d453bfcad44201b19a1cc3c77dba086b122a499d2d05f38af7961
3
+ size 9186304