Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
236
dacorvo HF staff commited on
Commit
6dd642e
•
1 Parent(s): 41a16cc

Synchronizing local compiler cache.

Browse files
Files changed (19) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/3671f4f6e9fb55e4d4fd.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/model.neff +0 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_4ce8517913f9dcb046db+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_4ce8517913f9dcb046db+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/compile_flags.txt +1 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/model.hlo.pb +3 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/model.neff +0 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/compile_flags.txt +1 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.hlo.pb +3 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/compile_flags.txt +1 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/model.hlo.pb +3 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/model.neff +0 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/compile_flags.txt +1 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.hlo.pb +3 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1006,3 +1006,5 @@ neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.neff fi
1006
  neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1007
  neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1008
  neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
1006
  neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1007
  neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1008
  neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1009
+ neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1010
+ neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/NousResearch/Llama-2-7b-chat-hf/3671f4f6e9fb55e4d4fd.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-7b-chat-hf", "checkpoint_revision": "37892f30c23786c0d5367d80481fa0d9fba93cf8"}}
neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c331d8f7d2f0356efe558952b285e2f564d669a72b88aafa0f2ae9b50a74cd
3
+ size 126648
neuronxcc-2.12.68.0+4480452af/MODULE_19799d9ddca515f1e2a3+2c2d707e/model.neff ADDED
Binary file (605 kB). View file
 
neuronxcc-2.12.68.0+4480452af/MODULE_4ce8517913f9dcb046db+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_4ce8517913f9dcb046db+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f2c3bd34fa9a666ecc7761e4de6afb32f6f0a5ad1e82f8f6a49fb85a725e5b8
3
+ size 126648
neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0f27a0c93fdf9411d96cfc5e9876fe04b13263780cbd6ed874372a4d49c678
3
+ size 126648
neuronxcc-2.12.68.0+4480452af/MODULE_78a708113a0abe3bb630+2c2d707e/model.neff ADDED
Binary file (554 kB). View file
 
neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65e10acdd5186bd49cc88f6ceed76bc84748ee6f076de343193b6be4534c210
3
+ size 297626
neuronxcc-2.12.68.0+4480452af/MODULE_9c7a263166e0f6950fe0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34bbf0325dcea2421ba7270bf30e7922a433ae8ae0aa2a21e146c92cd240177c
3
+ size 47197184
neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d77735245f5022081f65d03846d4ad1974acce8fc806795813b3122f0799a0b
3
+ size 126648
neuronxcc-2.12.68.0+4480452af/MODULE_abe31ef5026f14fa3772+2c2d707e/model.neff ADDED
Binary file (574 kB). View file
 
neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcd5ec203680dc9542cd1844a28f544e8c6ac9d72b4a94498c04cf285a93d59
3
+ size 300985
neuronxcc-2.12.68.0+4480452af/MODULE_b0880fb3960d07f95631+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6821744725d584b72d3b5419efe49a1471c329e73d1909789e6d76ae5059d7af
3
+ size 9186304