Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
155
dacorvo HF staff commited on
Commit
64bba01
•
1 Parent(s): b9c3969

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/mistral/teknium/OpenHermes-2.5-Mistral-7B/eda47d693eb609977c23.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1152,3 +1152,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_e0fa7a00c6c7a1e3fd45+2c2d707e/model.neff fi
1152
  neuronxcc-2.12.68.0+4480452af/MODULE_e18006d8d069baf3335c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1153
  neuronxcc-2.12.68.0+4480452af/MODULE_e568524f50e3326159ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1154
  neuronxcc-2.12.68.0+4480452af/MODULE_eeb720bfc447bc3a7295+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1152
  neuronxcc-2.12.68.0+4480452af/MODULE_e18006d8d069baf3335c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1153
  neuronxcc-2.12.68.0+4480452af/MODULE_e568524f50e3326159ef+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1154
  neuronxcc-2.12.68.0+4480452af/MODULE_eeb720bfc447bc3a7295+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1155
+ neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1156
+ neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/teknium/OpenHermes-2.5-Mistral-7B/eda47d693eb609977c23.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32002, "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": false, "rope_theta": 10000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 32000, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 2, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "teknium/OpenHermes-2.5-Mistral-7B", "checkpoint_revision": "24c0bea14d53e6f67f1fbe2eca5bfe7cae389b33"}}
neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1850fa696787b621371247383d92dfaa26d5e6be00a1dccff01f6d3f6e4b1c6
3
+ size 537246832
neuronxcc-2.12.68.0+4480452af/MODULE_d67a253483f476880ba6+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1051b8eed2e226b8a85ae807cd21365a157c747e16fd278009d33ff1c9e24691
3
+ size 113398784
neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62f63cc9e25b34aeb24fbd78b6f88d3462b421981245f877991001ab6824911
3
+ size 410840
neuronxcc-2.12.68.0+4480452af/MODULE_d69b0ea91f95fcacc9be+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8cd19287a2392bf8df1278bffc94e5a6f2df10d33f2651fee8234466a3e3e16
3
+ size 10732544