Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
270
dacorvo HF staff commited on
Commit
b9e751a
•
1 Parent(s): da5c4c8

Synchronizing local compiler cache.

Browse files
Files changed (8) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/05b1ba456b4330d6b05d.json +1 -0
  3. neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/model.hlo_module.pb +3 -0
  5. neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/model.hlo_module.pb +3 -0
  8. neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -3557,3 +3557,5 @@ neuronxcc-2.14.227.0+2d4f85be/MODULE_eca5b8624d9b982c886c+2c2d707e/model.neff fi
3557
  neuronxcc-2.14.227.0+2d4f85be/MODULE_faee8f7c39e1283eec5d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3558
  neuronxcc-2.14.227.0+2d4f85be/MODULE_0c2fdc29018dbc3b2a97+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3559
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d671762f3c3beb865edf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
3557
  neuronxcc-2.14.227.0+2d4f85be/MODULE_faee8f7c39e1283eec5d+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3558
  neuronxcc-2.14.227.0+2d4f85be/MODULE_0c2fdc29018dbc3b2a97+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3559
  neuronxcc-2.14.227.0+2d4f85be/MODULE_d671762f3c3beb865edf+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3560
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
3561
+ neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.14.227.0+2d4f85be/0_REGISTRY/0.0.24.dev0/inference/mistral/mistralai/Mistral-7B-Instruct-v0.3/05b1ba456b4330d6b05d.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.3", "checkpoint_revision": "708a0609e640ac1edfb9020a7c934f51d34d6c79", "compiler_type": "neuronx-cc", "compiler_version": "2.14.227.0+2d4f85be", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32768}
neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f4132e23a2bbfa30189abce89fa2c4547fbc944b86f1254b0090bb01b855694
3
+ size 360486
neuronxcc-2.14.227.0+2d4f85be/MODULE_75fab992bd356f9baea4+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35b4417c1df870e3bf017ef3662799b5c01ada1cb921ca88066c68a17cf1ad2
3
+ size 11080704
neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817136258f756733e915e8644ea983ddf680fbce8bb898e0dec04e70fb7e6875
3
+ size 307043
neuronxcc-2.14.227.0+2d4f85be/MODULE_d51fe5e835c77b574882+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf4a20c9cef42aee3888185867e206e66440fff9ca1985135d886ffbcc10994
3
+ size 9042944