Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
218
dacorvo HF staff commited on
Commit
1a19897
•
1 Parent(s): 9497e42

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/daaa8263f7776eb476dd.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1024,3 +1024,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_e3bfa9326cdfd6ea58d6+2c2d707e/model.neff fi
1024
  neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1025
  neuronxcc-2.12.68.0+4480452af/MODULE_13ce0aa1713a6579ebe5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1026
  neuronxcc-2.12.68.0+4480452af/MODULE_b9022a7120a9b15abca7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1024
  neuronxcc-2.12.68.0+4480452af/MODULE_f810d86474a28a97f337+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1025
  neuronxcc-2.12.68.0+4480452af/MODULE_13ce0aa1713a6579ebe5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1026
  neuronxcc-2.12.68.0+4480452af/MODULE_b9022a7120a9b15abca7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1027
+ neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+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
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/NousResearch/Llama-2-7b-chat-hf/daaa8263f7776eb476dd.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": 4, "num_cores": 2, "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_33b3843aad14a53dc9e8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d55b4d86b8c17f280141bdc256fc2cdba958394c8025e42c369181ded6d740
3
+ size 349039
neuronxcc-2.12.68.0+4480452af/MODULE_33b3843aad14a53dc9e8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fb88fa28be70e372ac55cb691e652f25a79d4c9a9686d0d9a2f0b3690bbf33
3
+ size 99963904
neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b9bee02b07641d02ff897b5e760eee66f049768db78f4c66a9265ef0ace63b9
3
+ size 393882
neuronxcc-2.12.68.0+4480452af/MODULE_a1817c3e64e277af5cdb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dca6c5023d3934235256ebbc0c886c61290d76e830a11de7b22b360818624c1
3
+ size 15012864