Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
266
dacorvo HF staff commited on
Commit
a1e45fe
•
1 Parent(s): a368c1d

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/gorilla-llm/gorilla-openfunctions-v2/c5c1e9c88e932bf1b928.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1539,3 +1539,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_b83cfc30dfa5bb3ba761+2c2d707e/model.neff fi
1539
  neuronxcc-2.12.68.0+4480452af/MODULE_c1a7e8c2edfdaa918c1e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1540
  neuronxcc-2.12.68.0+4480452af/MODULE_f09c704459103a4c46d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1541
  neuronxcc-2.12.68.0+4480452af/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1539
  neuronxcc-2.12.68.0+4480452af/MODULE_c1a7e8c2edfdaa918c1e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1540
  neuronxcc-2.12.68.0+4480452af/MODULE_f09c704459103a4c46d2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1541
  neuronxcc-2.12.68.0+4480452af/MODULE_fb6b30ee88e0de6dc73c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1542
+ neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1543
+ neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/gorilla-llm/gorilla-openfunctions-v2/c5c1e9c88e932bf1b928.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 102400, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 30, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "pretraining_tp": 1, "use_cache": false, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 100000, "eos_token_id": 100015, "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": "gorilla-llm/gorilla-openfunctions-v2", "checkpoint_revision": "0f91d705e64b77fb55e35a7eab5d03bf965c9b5c"}}
neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0b5a56b2cc8ec9c1a0f549fe6789d2e7f8ef6ca22ff61d6ff9b5dda2c3daca
3
+ size 327274
neuronxcc-2.12.68.0+4480452af/MODULE_629cd517574fc8495496+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621f5e773c74f8ff5da0390d7de677891d26c2cc79f25ac5973ad547929b6204
3
+ size 93860864
neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00a56449135e57f16beeda8e7538bc85f5079083cdc330a27a6b00dfacf634d
3
+ size 369364
neuronxcc-2.12.68.0+4480452af/MODULE_6cecfbbc43a845835581+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb094977d6c3fa8fcb992cd355f7f1c5bd5027536bb22d9bd7ab6155d6c70681
3
+ size 15197184