Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
209
dacorvo HF staff commited on
Commit
9eee0cc
•
1 Parent(s): aafcbb8

Synchronizing local compiler cache.

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/openchat/openchat-3.5-0106/acf18f45c9fad777c525.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.log +1 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.neff +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/compile_flags.txt +1 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.hlo.pb +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1628,3 +1628,4 @@ neuronxcc-2.12.68.0+4480452af/MODULE_859cab849c50636114da+2c2d707e/model.neff fi
1628
  neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1629
  neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1630
  neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
1628
  neuronxcc-2.12.68.0+4480452af/MODULE_8f70362d8b00671023b5+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1629
  neuronxcc-2.12.68.0+4480452af/MODULE_f430b7ca17750e9e0537+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1630
  neuronxcc-2.12.68.0+4480452af/MODULE_fe659df92d8bbe70a5fb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1631
+ neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/openchat/openchat-3.5-0106/acf18f45c9fad777c525.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32002, "max_position_embeddings": 8192, "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": 32000, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "bf16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "openchat/openchat-3.5-0106", "checkpoint_revision": "9619fb7d2a8e25fa6b0633c0f57f7f4aa79b45c4"}}
neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ff27e014ceee769ed4c1083ce47db0f4d10af9d911bd727b2a02236c5e3239
3
+ size 671558352
neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.log ADDED
@@ -0,0 +1 @@
 
 
1
+ Failed compilation with ['neuronx-cc', '--target=trn1', 'compile', '--framework', 'XLA', '/tmp/ubuntu/neuroncc_compile_workdir/0ae8dbb8-cd66-42d3-9f53-728b91c5d83f/model.MODULE_8266fa9a2b34b562a688+2c2d707e.hlo.pb', '--output', '/tmp/ubuntu/neuroncc_compile_workdir/0ae8dbb8-cd66-42d3-9f53-728b91c5d83f/model.MODULE_8266fa9a2b34b562a688+2c2d707e.neff', '--model-type=transformer', '--auto-cast=none', '--verbose=35']: 2024-03-21T18:23:29Z [LUR015] Compiler generated too many instructions (5703234). This maybe due to a failure in parallelism extraction by the tensorizer. - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new
neuronxcc-2.12.68.0+4480452af/MODULE_8266fa9a2b34b562a688+2c2d707e/model.neff ADDED
@@ -0,0 +1 @@
 
 
1
+ ERROR
neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d211eb2a82ff7d8583f05c66d6ab2088a99b9e7bac36dda8ac6bf93f07e3f15
3
+ size 513170
neuronxcc-2.12.68.0+4480452af/MODULE_c8876a38481af5daf13a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d591441a6c6c1a1236499e633c87cd101a29a8fe3c93e94caa53f73554103a6d
3
+ size 13261824