Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
4935a66
•
1 Parent(s): e38a6c4

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/f8181648f59d3bf10328.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1028,3 +1028,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.neff fi
1028
  neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1029
  neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1030
  neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1028
  neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1029
  neuronxcc-2.12.68.0+4480452af/MODULE_1c1d77805b9403cfbfdd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1030
  neuronxcc-2.12.68.0+4480452af/MODULE_1c6b7b83399937bb2d13+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1031
+ neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1032
+ neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/f8181648f59d3bf10328.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, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 8, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8"}}
neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e78e2df5c6818db51b96d72107ecd2e4bda8d41fbd5f0800edcd09a4244bb5
3
+ size 394266
neuronxcc-2.12.68.0+4480452af/MODULE_ca9eb83b779366088099+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b936ba8d70118187068e98168e2c1969b2accb5d3b2b84fc5d9224d05be2b6c
3
+ size 6083584
neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:627dc0bd21c02e53fd3a8a675be8f2767af9ba3dd2cf8fffcbbb8547a3ce6cd5
3
+ size 349423
neuronxcc-2.12.68.0+4480452af/MODULE_e1fdb4d7a71179cccd05+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903041cfa79abdeb4497717ed07dc23805dff1db21ccd81299b09f1a8f680a86
3
+ size 30598144