Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
268
dacorvo HF staff commited on
Commit
8781979
•
1 Parent(s): d09b7dd

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/7cf5159a98ef6aa54442.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2360,3 +2360,5 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.neff fi
2360
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2361
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2362
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
2360
  neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2361
  neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2362
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2363
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2364
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/7cf5159a98ef6aa54442.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "561487d18c41c76bcb5fc6cfb73a324982f04f47", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d674a2f08b71ca6a5e3c52090031be9b0741e4f6f73e5cdfdb7e1f91ed59c64
3
+ size 398979
neuronxcc-2.13.66.0+6dfecc895/MODULE_4f36f9e3469b0c2257ca+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96ae6ddcb0247f0ead57b5001ac2b52c652a5014a24cd4d3233b16acce84b75
3
+ size 12381184
neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cff4ba8b7a13990a4ba7cba3394b92afb4a6caa2f0783ceb723d13789632bb7
3
+ size 345623
neuronxcc-2.13.66.0+6dfecc895/MODULE_ab8241181adbc5ea8099+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bb8f1d44b70d63f3dad3125a30e1bcc375dc9589204a76c91a5666c40e1abb
3
+ size 13190144