Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
653321e
•
1 Parent(s): db5e3b4

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/mistral/mistralai/Mistral-7B-Instruct-v0.1/170712e438c4a273b89e.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1042,3 +1042,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_462374838ef2c0e86b3e+2c2d707e/model.neff fi
1042
  neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1043
  neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1044
  neuronxcc-2.12.68.0+4480452af/MODULE_bcba395a7a65790b3f7b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1042
  neuronxcc-2.12.68.0+4480452af/MODULE_5cb9029fdc387a80baa4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1043
  neuronxcc-2.12.68.0+4480452af/MODULE_07f04326f582ccad6a0f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1044
  neuronxcc-2.12.68.0+4480452af/MODULE_bcba395a7a65790b3f7b+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1045
+ neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1046
+ neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/mistral/mistralai/Mistral-7B-Instruct-v0.1/170712e438c4a273b89e.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": 4096, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 8, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.1", "checkpoint_revision": "9ab9e76e2b09f9f29ea2d56aa5bd139e4445c59e"}}
neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34d37512b2db70a045e27b25d7da4ee332f62140787926af173065a36eb9172
3
+ size 537247216
neuronxcc-2.12.68.0+4480452af/MODULE_8b51cf18d62d468344e3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5949e92f52fdb61c6413bda9d7215301445365b14d486ac17658d85cf33dec56
3
+ size 36250624
neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9de6fbc83fb6d1538c7cce853a60e3e25be56fb2b5738b16f60ae3f8ae691df
3
+ size 411224
neuronxcc-2.12.68.0+4480452af/MODULE_c841b9dc96a94194571a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a2c26b76e6b6cab80174af5853fbc5b560693d9bb45bef5687bea7f5b64e0d
3
+ size 3339264