Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
242
dacorvo HF staff commited on
Commit
767e66e
•
1 Parent(s): c970eaa

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-2-13b-chat-hf/310f9b818b9630a85eab.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1052,3 +1052,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_0f9126efc1ea0f6120f1+2c2d707e/model.neff fi
1052
  neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1053
  neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1054
  neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1052
  neuronxcc-2.12.68.0+4480452af/MODULE_78246301f6d50b468294+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1053
  neuronxcc-2.12.68.0+4480452af/MODULE_bc7cec3dee03f45226ae+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1054
  neuronxcc-2.12.68.0+4480452af/MODULE_c19a423f9f0c88c2affc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1055
+ neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1056
+ neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+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-2-13b-chat-hf/310f9b818b9630a85eab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "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": 1, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f"}}
neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619e9f1b40c46eaffab0d276ee73667e924baea8735049bf85b543cadda3c2fa
3
+ size 373514
neuronxcc-2.12.68.0+4480452af/MODULE_613d40b655171e52e4ed+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0e3aae20e29771142caa818dff61353e31c4a405c27e3d4ca1a9e7f5c9c19d8
3
+ size 13702144
neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f48dc7ed110b78f990b7de2ac7f27e2e0b8e6cabcb11232d3be78cb409ccb59
3
+ size 377729
neuronxcc-2.12.68.0+4480452af/MODULE_d5a114d6ffc6fa2a086c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4adc05e00c292c24d0b1b03f1d84fe19a27fe11b4e3882385b781545c687d5f8
3
+ size 2479104