Add content

README.md

@@ -0,0 +1,14 @@
+
+A set of 50% weight-sparse Llama3.1-8B pruned by [Wanda](https://github.com/locuslab/wanda).
+Model links are in the table below. Models can be loaded as is with Huggingface Transformers.
+
+### Perplexity
+![Perplexity over Sparsity](llama3.1-8B_Wanda_sparsity.png)
+### MMLU (5-shot)
+| MMLU (5-shot)  | Accuracy (%) | Relative to Dense (%) | Model Link|
+|----------------|--------------|-----------------------|-----------|
+| Dense          | 65.1         | baseline              | [Meta-Llama-3.1-8B-wanda-unstructured-0.0](https://huggingface.co/vuiseng9/Meta-Llama-3.1-8B-wanda-unstructured-0.0) |
+| Unstructured   | 50.0         | -15.1                 | [Meta-Llama-3.1-8B-wanda-unstructured-0.5](https://huggingface.co/vuiseng9/Meta-Llama-3.1-8B-wanda-unstructured-0.5) |
+| 4:8            | 39.3         | -25.8                 | [Meta-Llama-3.1-8B-wanda-4of8](https://huggingface.co/vuiseng9/Meta-Llama-3.1-8B-wanda-4of8) |
+| 2:4            | 28.7         | -36.4                 | [Meta-Llama-3.1-8B-wanda-2of4](https://huggingface.co/vuiseng9/Meta-Llama-3.1-8B-wanda-2of4) |
+

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

log_wanda.txt

@@ -0,0 +1,2 @@
+method	actual_sparsity	ppl_test
+wanda	0.5000	12.8304

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3374be1d1ad64e845e7ad5b7006709a28eb29010339abf50833343526cfd34
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce69bc94726e5c64d69c08f3aaf17bf5bc2cdc868a8c5165a51374c7bae594e0
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e73ed8d4a14c46afc841f7011998d16d1efb856f1c3e4b05a525bee45248d22
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9210a786239ca7428c2e31ea696aad3656aee54a68fcdaba04d9b6253cee1bca
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

pruning_args.json

@@ -0,0 +1,13 @@
+{
+    "model": "meta-llama/Meta-Llama-3.1-8B",
+    "seed": 0,
+    "nsamples": 128,
+    "sparsity_ratio": 0.5,
+    "sparsity_type": "4:8",
+    "prune_method": "wanda",
+    "cache_dir": null,
+    "use_variant": false,
+    "save": "/data2/vchua/run/hgx1-240823-wanda/wanda-ed/meta-llama/Meta-Llama-3.1-8B-wanda-4:8-0.5",
+    "save_model": true,
+    "eval_zero_shot": false
+}

sparsity_report_Meta-Llama-3.1-8B-wanda-4:8-0.5.csv

@@ -0,0 +1,226 @@
+row,layer_id,short_id,layer_type,param_type,shape,nparam,nnz,sparsity,tile_shape,n_tile,n_tile_total,tile_avg,tile_min,tile_med,tile_max,col_avg,col_min,col_med,col_max,row_avg,row_min,row_med,row_max
+0,model.layers.0.self_attn.q_proj,tx.0.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.4375,1.0,0.5,0.5,0.5,0.5
+1,model.layers.0.self_attn.k_proj,tx.0.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.4375,1.0,0.5,0.5,0.5,0.5
+2,model.layers.0.self_attn.v_proj,tx.0.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.3984375,1.0,0.5,0.5,0.5,0.5
+3,model.layers.0.self_attn.o_proj,tx.0.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.9765625,0.5,0.5,0.5,0.5
+4,model.layers.0.mlp.gate_proj,tx.0.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0703125,0.5078125,1.0,0.5,0.5,0.5,0.5
+5,model.layers.0.mlp.up_proj,tx.0.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0859375,0.5078125,1.0,0.5,0.5,0.5,0.5
+6,model.layers.0.mlp.down_proj,tx.0.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.9375,0.5,0.5,0.5,0.5
+7,model.layers.1.self_attn.q_proj,tx.1.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.53125,1.0,0.5,0.5,0.5,0.5
+8,model.layers.1.self_attn.k_proj,tx.1.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.53125,1.0,0.5,0.5,0.5,0.5
+9,model.layers.1.self_attn.v_proj,tx.1.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,1.0,0.5,0.5,0.5,0.5
+10,model.layers.1.self_attn.o_proj,tx.1.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.953125,0.5,0.5,0.5,0.5
+11,model.layers.1.mlp.gate_proj,tx.1.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1171875,0.5078125,1.0,0.5,0.5,0.5,0.5
+12,model.layers.1.mlp.up_proj,tx.1.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1171875,0.5078125,1.0,0.5,0.5,0.5,0.5
+13,model.layers.1.mlp.down_proj,tx.1.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.859375,0.5,0.5,0.5,0.5
+14,model.layers.2.self_attn.q_proj,tx.2.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.53125,1.0,0.5,0.5,0.5,0.5
+15,model.layers.2.self_attn.k_proj,tx.2.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.53125,1.0,0.5,0.5,0.5,0.5
+16,model.layers.2.self_attn.v_proj,tx.2.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.03125,0.5234375,1.0,0.5,0.5,0.5,0.5
+17,model.layers.2.self_attn.o_proj,tx.2.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.9375,0.5,0.5,0.5,0.5
+18,model.layers.2.mlp.gate_proj,tx.2.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1015625,0.5,1.0,0.5,0.5,0.5,0.5
+19,model.layers.2.mlp.up_proj,tx.2.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1484375,0.5,1.0,0.5,0.5,0.5,0.5
+20,model.layers.2.mlp.down_proj,tx.2.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,0.875,0.5,0.5,0.5,0.5
+21,model.layers.3.self_attn.q_proj,tx.3.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,1.0,0.5,0.5,0.5,0.5
+22,model.layers.3.self_attn.k_proj,tx.3.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5234375,1.0,0.5,0.5,0.5,0.5
+23,model.layers.3.self_attn.v_proj,tx.3.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0625,0.515625,1.0,0.5,0.5,0.5,0.5
+24,model.layers.3.self_attn.o_proj,tx.3.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.8828125,0.5,0.5,0.5,0.5
+25,model.layers.3.mlp.gate_proj,tx.3.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0703125,0.5,1.0,0.5,0.5,0.5,0.5
+26,model.layers.3.mlp.up_proj,tx.3.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1640625,0.5,1.0,0.5,0.5,0.5,0.5
+27,model.layers.3.mlp.down_proj,tx.3.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.890625,0.5,0.5,0.5,0.5
+28,model.layers.4.self_attn.q_proj,tx.4.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,1.0,0.5,0.5,0.5,0.5
+29,model.layers.4.self_attn.k_proj,tx.4.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,1.0,0.5,0.5,0.5,0.5
+30,model.layers.4.self_attn.v_proj,tx.4.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0390625,0.515625,1.0,0.5,0.5,0.5,0.5
+31,model.layers.4.self_attn.o_proj,tx.4.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9296875,0.5,0.5,0.5,0.5
+32,model.layers.4.mlp.gate_proj,tx.4.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,1.0,0.5,0.5,0.5,0.5
+33,model.layers.4.mlp.up_proj,tx.4.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1328125,0.5,1.0,0.5,0.5,0.5,0.5
+34,model.layers.4.mlp.down_proj,tx.4.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5,0.90625,0.5,0.5,0.5,0.5
+35,model.layers.5.self_attn.q_proj,tx.5.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,0.953125,0.5,0.5,0.5,0.5
+36,model.layers.5.self_attn.k_proj,tx.5.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,0.9453125,0.5,0.5,0.5,0.5
+37,model.layers.5.self_attn.v_proj,tx.5.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.046875,0.515625,1.0,0.5,0.5,0.5,0.5
+38,model.layers.5.self_attn.o_proj,tx.5.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8671875,0.5,0.5,0.5,0.5
+39,model.layers.5.mlp.gate_proj,tx.5.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,1.0,0.5,0.5,0.5,0.5
+40,model.layers.5.mlp.up_proj,tx.5.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0859375,0.5,1.0,0.5,0.5,0.5,0.5
+41,model.layers.5.mlp.down_proj,tx.5.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.890625,0.5,0.5,0.5,0.5
+42,model.layers.6.self_attn.q_proj,tx.6.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.890625,0.5,0.5,0.5,0.5
+43,model.layers.6.self_attn.k_proj,tx.6.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5234375,0.8984375,0.5,0.5,0.5,0.5
+44,model.layers.6.self_attn.v_proj,tx.6.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0625,0.5078125,1.0,0.5,0.5,0.5,0.5
+45,model.layers.6.self_attn.o_proj,tx.6.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.921875,0.5,0.5,0.5,0.5
+46,model.layers.6.mlp.gate_proj,tx.6.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,1.0,0.5,0.5,0.5,0.5
+47,model.layers.6.mlp.up_proj,tx.6.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.078125,0.5,1.0,0.5,0.5,0.5,0.5
+48,model.layers.6.mlp.down_proj,tx.6.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5,0.9140625,0.5,0.5,0.5,0.5
+49,model.layers.7.self_attn.q_proj,tx.7.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.8359375,0.5,0.5,0.5,0.5
+50,model.layers.7.self_attn.k_proj,tx.7.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.875,0.5,0.5,0.5,0.5
+51,model.layers.7.self_attn.v_proj,tx.7.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0546875,0.5078125,0.9921875,0.5,0.5,0.5,0.5
+52,model.layers.7.self_attn.o_proj,tx.7.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,0.8828125,0.5,0.5,0.5,0.5
+53,model.layers.7.mlp.gate_proj,tx.7.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.78125,0.5,0.5,0.5,0.5
+54,model.layers.7.mlp.up_proj,tx.7.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0859375,0.5,0.734375,0.5,0.5,0.5,0.5
+55,model.layers.7.mlp.down_proj,tx.7.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5,0.9375,0.5,0.5,0.5,0.5
+56,model.layers.8.self_attn.q_proj,tx.8.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+57,model.layers.8.self_attn.k_proj,tx.8.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8671875,0.5,0.5,0.5,0.5
+58,model.layers.8.self_attn.v_proj,tx.8.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.9921875,0.5,0.5,0.5,0.5
+59,model.layers.8.self_attn.o_proj,tx.8.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.046875,0.515625,0.921875,0.5,0.5,0.5,0.5
+60,model.layers.8.mlp.gate_proj,tx.8.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,1.0,0.5,0.5,0.5,0.5
+61,model.layers.8.mlp.up_proj,tx.8.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.078125,0.5,1.0,0.5,0.5,0.5,0.5
+62,model.layers.8.mlp.down_proj,tx.8.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.921875,0.5,0.5,0.5,0.5
+63,model.layers.9.self_attn.q_proj,tx.9.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+64,model.layers.9.self_attn.k_proj,tx.9.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.890625,0.5,0.5,0.5,0.5
+65,model.layers.9.self_attn.v_proj,tx.9.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0625,0.5,0.9921875,0.5,0.5,0.5,0.5
+66,model.layers.9.self_attn.o_proj,tx.9.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.046875,0.515625,0.859375,0.5,0.5,0.5,0.5
+67,model.layers.9.mlp.gate_proj,tx.9.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.75,0.5,0.5,0.5,0.5
+68,model.layers.9.mlp.up_proj,tx.9.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0703125,0.5,0.7578125,0.5,0.5,0.5,0.5
+69,model.layers.9.mlp.down_proj,tx.9.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.8984375,0.5,0.5,0.5,0.5
+70,model.layers.10.self_attn.q_proj,tx.10.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.859375,0.5,0.5,0.5,0.5
+71,model.layers.10.self_attn.k_proj,tx.10.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8671875,0.5,0.5,0.5,0.5
+72,model.layers.10.self_attn.v_proj,tx.10.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0703125,0.5,0.9921875,0.5,0.5,0.5,0.5
+73,model.layers.10.self_attn.o_proj,tx.10.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.8515625,0.5,0.5,0.5,0.5
+74,model.layers.10.mlp.gate_proj,tx.10.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.75,0.5,0.5,0.5,0.5
+75,model.layers.10.mlp.up_proj,tx.10.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.09375,0.5,0.7578125,0.5,0.5,0.5,0.5
+76,model.layers.10.mlp.down_proj,tx.10.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8828125,0.5,0.5,0.5,0.5
+77,model.layers.11.self_attn.q_proj,tx.11.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8828125,0.5,0.5,0.5,0.5
+78,model.layers.11.self_attn.k_proj,tx.11.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9296875,0.5,0.5,0.5,0.5
+79,model.layers.11.self_attn.v_proj,tx.11.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.09375,0.5,0.9921875,0.5,0.5,0.5,0.5
+80,model.layers.11.self_attn.o_proj,tx.11.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.03125,0.515625,0.8984375,0.5,0.5,0.5,0.5
+81,model.layers.11.mlp.gate_proj,tx.11.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.7578125,0.5,0.5,0.5,0.5
+82,model.layers.11.mlp.up_proj,tx.11.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.1015625,0.5,0.796875,0.5,0.5,0.5,0.5
+83,model.layers.11.mlp.down_proj,tx.11.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.8828125,0.5,0.5,0.5,0.5
+84,model.layers.12.self_attn.q_proj,tx.12.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+85,model.layers.12.self_attn.k_proj,tx.12.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.9140625,0.5,0.5,0.5,0.5
+86,model.layers.12.self_attn.v_proj,tx.12.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5,0.9921875,0.5,0.5,0.5,0.5
+87,model.layers.12.self_attn.o_proj,tx.12.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.84375,0.5,0.5,0.5,0.5
+88,model.layers.12.mlp.gate_proj,tx.12.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.75,0.5,0.5,0.5,0.5
+89,model.layers.12.mlp.up_proj,tx.12.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0859375,0.5,0.75,0.5,0.5,0.5,0.5
+90,model.layers.12.mlp.down_proj,tx.12.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9140625,0.5,0.5,0.5,0.5
+91,model.layers.13.self_attn.q_proj,tx.13.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9296875,0.5,0.5,0.5,0.5
+92,model.layers.13.self_attn.k_proj,tx.13.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.9453125,0.5,0.5,0.5,0.5
+93,model.layers.13.self_attn.v_proj,tx.13.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.078125,0.5,0.9921875,0.5,0.5,0.5,0.5
+94,model.layers.13.self_attn.o_proj,tx.13.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0625,0.515625,0.8671875,0.5,0.5,0.5,0.5
+95,model.layers.13.mlp.gate_proj,tx.13.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.75,0.5,0.5,0.5,0.5
+96,model.layers.13.mlp.up_proj,tx.13.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0859375,0.5,0.734375,0.5,0.5,0.5,0.5
+97,model.layers.13.mlp.down_proj,tx.13.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.90625,0.5,0.5,0.5,0.5
+98,model.layers.14.self_attn.q_proj,tx.14.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.890625,0.5,0.5,0.5,0.5
+99,model.layers.14.self_attn.k_proj,tx.14.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9609375,0.5,0.5,0.5,0.5
+100,model.layers.14.self_attn.v_proj,tx.14.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.9921875,0.5,0.5,0.5,0.5
+101,model.layers.14.self_attn.o_proj,tx.14.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+102,model.layers.14.mlp.gate_proj,tx.14.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.7421875,0.5,0.5,0.5,0.5
+103,model.layers.14.mlp.up_proj,tx.14.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.734375,0.5,0.5,0.5,0.5
+104,model.layers.14.mlp.down_proj,tx.14.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.921875,0.5,0.5,0.5,0.5
+105,model.layers.15.self_attn.q_proj,tx.15.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.859375,0.5,0.5,0.5,0.5
+106,model.layers.15.self_attn.k_proj,tx.15.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.8984375,0.5,0.5,0.5,0.5
+107,model.layers.15.self_attn.v_proj,tx.15.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,1.0,0.5,0.5,0.5,0.5
+108,model.layers.15.self_attn.o_proj,tx.15.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8359375,0.5,0.5,0.5,0.5
+109,model.layers.15.mlp.gate_proj,tx.15.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.7578125,0.5,0.5,0.5,0.5
+110,model.layers.15.mlp.up_proj,tx.15.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.7421875,0.5,0.5,0.5,0.5
+111,model.layers.15.mlp.down_proj,tx.15.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.9296875,0.5,0.5,0.5,0.5
+112,model.layers.16.self_attn.q_proj,tx.16.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8515625,0.5,0.5,0.5,0.5
+113,model.layers.16.self_attn.k_proj,tx.16.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.9140625,0.5,0.5,0.5,0.5
+114,model.layers.16.self_attn.v_proj,tx.16.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.9921875,0.5,0.5,0.5,0.5
+115,model.layers.16.self_attn.o_proj,tx.16.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0546875,0.5078125,0.8203125,0.5,0.5,0.5,0.5
+116,model.layers.16.mlp.gate_proj,tx.16.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.765625,0.5,0.5,0.5,0.5
+117,model.layers.16.mlp.up_proj,tx.16.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8125,0.5,0.5,0.5,0.5
+118,model.layers.16.mlp.down_proj,tx.16.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+119,model.layers.17.self_attn.q_proj,tx.17.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.8515625,0.5,0.5,0.5,0.5
+120,model.layers.17.self_attn.k_proj,tx.17.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8671875,0.5,0.5,0.5,0.5
+121,model.layers.17.self_attn.v_proj,tx.17.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0625,0.5078125,1.0,0.5,0.5,0.5,0.5
+122,model.layers.17.self_attn.o_proj,tx.17.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8828125,0.5,0.5,0.5,0.5
+123,model.layers.17.mlp.gate_proj,tx.17.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.7890625,0.5,0.5,0.5,0.5
+124,model.layers.17.mlp.up_proj,tx.17.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.828125,0.5,0.5,0.5,0.5
+125,model.layers.17.mlp.down_proj,tx.17.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0546875,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+126,model.layers.18.self_attn.q_proj,tx.18.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.84375,0.5,0.5,0.5,0.5
+127,model.layers.18.self_attn.k_proj,tx.18.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8828125,0.5,0.5,0.5,0.5
+128,model.layers.18.self_attn.v_proj,tx.18.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,1.0,0.5,0.5,0.5,0.5
+129,model.layers.18.self_attn.o_proj,tx.18.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.84375,0.5,0.5,0.5,0.5
+130,model.layers.18.mlp.gate_proj,tx.18.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.7890625,0.5,0.5,0.5,0.5
+131,model.layers.18.mlp.up_proj,tx.18.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.8359375,0.5,0.5,0.5,0.5
+132,model.layers.18.mlp.down_proj,tx.18.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.921875,0.5,0.5,0.5,0.5
+133,model.layers.19.self_attn.q_proj,tx.19.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.84375,0.5,0.5,0.5,0.5
+134,model.layers.19.self_attn.k_proj,tx.19.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8515625,0.5,0.5,0.5,0.5
+135,model.layers.19.self_attn.v_proj,tx.19.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,1.0,0.5,0.5,0.5,0.5
+136,model.layers.19.self_attn.o_proj,tx.19.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+137,model.layers.19.mlp.gate_proj,tx.19.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.828125,0.5,0.5,0.5,0.5
+138,model.layers.19.mlp.up_proj,tx.19.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+139,model.layers.19.mlp.down_proj,tx.19.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+140,model.layers.20.self_attn.q_proj,tx.20.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8125,0.5,0.5,0.5,0.5
+141,model.layers.20.self_attn.k_proj,tx.20.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.8984375,0.5,0.5,0.5,0.5
+142,model.layers.20.self_attn.v_proj,tx.20.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,1.0,0.5,0.5,0.5,0.5
+143,model.layers.20.self_attn.o_proj,tx.20.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.84375,0.5,0.5,0.5,0.5
+144,model.layers.20.mlp.gate_proj,tx.20.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8046875,0.5,0.5,0.5,0.5
+145,model.layers.20.mlp.up_proj,tx.20.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.84375,0.5,0.5,0.5,0.5
+146,model.layers.20.mlp.down_proj,tx.20.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.875,0.5,0.5,0.5,0.5
+147,model.layers.21.self_attn.q_proj,tx.21.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8203125,0.5,0.5,0.5,0.5
+148,model.layers.21.self_attn.k_proj,tx.21.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.828125,0.5,0.5,0.5,0.5
+149,model.layers.21.self_attn.v_proj,tx.21.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,1.0,0.5,0.5,0.5,0.5
+150,model.layers.21.self_attn.o_proj,tx.21.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+151,model.layers.21.mlp.gate_proj,tx.21.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.828125,0.5,0.5,0.5,0.5
+152,model.layers.21.mlp.up_proj,tx.21.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0546875,0.5078125,0.84375,0.5,0.5,0.5,0.5
+153,model.layers.21.mlp.down_proj,tx.21.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,0.8828125,0.5,0.5,0.5,0.5
+154,model.layers.22.self_attn.q_proj,tx.22.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0078125,0.515625,0.8125,0.5,0.5,0.5,0.5
+155,model.layers.22.self_attn.k_proj,tx.22.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.859375,0.5,0.5,0.5,0.5
+156,model.layers.22.self_attn.v_proj,tx.22.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.03125,0.515625,1.0,0.5,0.5,0.5,0.5
+157,model.layers.22.self_attn.o_proj,tx.22.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8046875,0.5,0.5,0.5,0.5
+158,model.layers.22.mlp.gate_proj,tx.22.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8046875,0.5,0.5,0.5,0.5
+159,model.layers.22.mlp.up_proj,tx.22.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.8125,0.5,0.5,0.5,0.5
+160,model.layers.22.mlp.down_proj,tx.22.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,0.8671875,0.5,0.5,0.5,0.5
+161,model.layers.23.self_attn.q_proj,tx.23.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8203125,0.5,0.5,0.5,0.5
+162,model.layers.23.self_attn.k_proj,tx.23.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.859375,0.5,0.5,0.5,0.5
+163,model.layers.23.self_attn.v_proj,tx.23.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0390625,0.515625,1.0,0.5,0.5,0.5,0.5
+164,model.layers.23.self_attn.o_proj,tx.23.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.8125,0.5,0.5,0.5,0.5
+165,model.layers.23.mlp.gate_proj,tx.23.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.8359375,0.5,0.5,0.5,0.5
+166,model.layers.23.mlp.up_proj,tx.23.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+167,model.layers.23.mlp.down_proj,tx.23.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.015625,0.5234375,0.90625,0.5,0.5,0.5,0.5
+168,model.layers.24.self_attn.q_proj,tx.24.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8203125,0.5,0.5,0.5,0.5
+169,model.layers.24.self_attn.k_proj,tx.24.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.875,0.5,0.5,0.5,0.5
+170,model.layers.24.self_attn.v_proj,tx.24.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.515625,1.0,0.5,0.5,0.5,0.5
+171,model.layers.24.self_attn.o_proj,tx.24.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.8203125,0.5,0.5,0.5,0.5
+172,model.layers.24.mlp.gate_proj,tx.24.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.84375,0.5,0.5,0.5,0.5
+173,model.layers.24.mlp.up_proj,tx.24.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0390625,0.5078125,0.890625,0.5,0.5,0.5,0.5
+174,model.layers.24.mlp.down_proj,tx.24.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.8828125,0.5,0.5,0.5,0.5
+175,model.layers.25.self_attn.q_proj,tx.25.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.828125,0.5,0.5,0.5,0.5
+176,model.layers.25.self_attn.k_proj,tx.25.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.859375,0.5,0.5,0.5,0.5
+177,model.layers.25.self_attn.v_proj,tx.25.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,1.0,0.5,0.5,0.5,0.5
+178,model.layers.25.self_attn.o_proj,tx.25.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.875,0.5,0.5,0.5,0.5
+179,model.layers.25.mlp.gate_proj,tx.25.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.84375,0.5,0.5,0.5,0.5
+180,model.layers.25.mlp.up_proj,tx.25.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+181,model.layers.25.mlp.down_proj,tx.25.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,0.875,0.5,0.5,0.5,0.5
+182,model.layers.26.self_attn.q_proj,tx.26.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.8515625,0.5,0.5,0.5,0.5
+183,model.layers.26.self_attn.k_proj,tx.26.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.890625,0.5,0.5,0.5,0.5
+184,model.layers.26.self_attn.v_proj,tx.26.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,1.0,0.5,0.5,0.5,0.5
+185,model.layers.26.self_attn.o_proj,tx.26.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.9140625,0.5,0.5,0.5,0.5
+186,model.layers.26.mlp.gate_proj,tx.26.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.875,0.5,0.5,0.5,0.5
+187,model.layers.26.mlp.up_proj,tx.26.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+188,model.layers.26.mlp.down_proj,tx.26.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5234375,0.8984375,0.5,0.5,0.5,0.5
+189,model.layers.27.self_attn.q_proj,tx.27.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,1.0,0.5,0.5,0.5,0.5
+190,model.layers.27.self_attn.k_proj,tx.27.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,1.0,0.5,0.5,0.5,0.5
+191,model.layers.27.self_attn.v_proj,tx.27.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.515625,1.0,0.5,0.5,0.5,0.5
+192,model.layers.27.self_attn.o_proj,tx.27.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5,0.859375,0.5,0.5,0.5,0.5
+193,model.layers.27.mlp.gate_proj,tx.27.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.7890625,0.5,0.5,0.5,0.5
+194,model.layers.27.mlp.up_proj,tx.27.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.8359375,0.5,0.5,0.5,0.5
+195,model.layers.27.mlp.down_proj,tx.27.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.53125,0.90625,0.5,0.5,0.5,0.5
+196,model.layers.28.self_attn.q_proj,tx.28.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.84375,0.5,0.5,0.5,0.5
+197,model.layers.28.self_attn.k_proj,tx.28.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.859375,0.5,0.5,0.5,0.5
+198,model.layers.28.self_attn.v_proj,tx.28.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,1.0,0.5,0.5,0.5,0.5
+199,model.layers.28.self_attn.o_proj,tx.28.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.8046875,0.5,0.5,0.5,0.5
+200,model.layers.28.mlp.gate_proj,tx.28.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.8203125,0.5,0.5,0.5,0.5
+201,model.layers.28.mlp.up_proj,tx.28.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.8125,0.5,0.5,0.5,0.5
+202,model.layers.28.mlp.down_proj,tx.28.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.53125,0.9375,0.5,0.5,0.5,0.5
+203,model.layers.29.self_attn.q_proj,tx.29.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,1.0,0.5,0.5,0.5,0.5
+204,model.layers.29.self_attn.k_proj,tx.29.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,1.0,0.5,0.5,0.5,0.5
+205,model.layers.29.self_attn.v_proj,tx.29.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,1.0,0.5,0.5,0.5,0.5
+206,model.layers.29.self_attn.o_proj,tx.29.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.8046875,0.5,0.5,0.5,0.5
+207,model.layers.29.mlp.gate_proj,tx.29.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5078125,0.84375,0.5,0.5,0.5,0.5
+208,model.layers.29.mlp.up_proj,tx.29.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0234375,0.5078125,0.8515625,0.5,0.5,0.5,0.5
+209,model.layers.29.mlp.down_proj,tx.29.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.53125,0.9453125,0.5,0.5,0.5,0.5
+210,model.layers.30.self_attn.q_proj,tx.30.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.84375,0.5,0.5,0.5,0.5
+211,model.layers.30.self_attn.k_proj,tx.30.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.5234375,0.890625,0.5,0.5,0.5,0.5
+212,model.layers.30.self_attn.v_proj,tx.30.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,1.0,0.5,0.5,0.5,0.5
+213,model.layers.30.self_attn.o_proj,tx.30.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.84375,0.5,0.5,0.5,0.5
+214,model.layers.30.mlp.gate_proj,tx.30.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,0.9453125,0.5,0.5,0.5,0.5
+215,model.layers.30.mlp.up_proj,tx.30.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.03125,0.5078125,0.8671875,0.5,0.5,0.5,0.5
+216,model.layers.30.mlp.down_proj,tx.30.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5390625,0.984375,0.5,0.5,0.5,0.5
+217,model.layers.31.self_attn.q_proj,tx.31.attn.q,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.9296875,0.5,0.5,0.5,0.5
+218,model.layers.31.self_attn.k_proj,tx.31.attn.k,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0,0.515625,0.9375,0.5,0.5,0.5,0.5
+219,model.layers.31.self_attn.v_proj,tx.31.attn.v,Linear,weight,"[1024, 4096]",4194304,2097152,0.5,"(128, 16)",8 x 256,2048,0.5,0.5,0.5,0.5,0.5,0.0078125,0.5078125,1.0,0.5,0.5,0.5,0.5
+220,model.layers.31.self_attn.o_proj,tx.31.attn.o,Linear,weight,"[4096, 4096]",16777216,8388608,0.5,"(128, 16)",32 x 256,8192,0.5,0.5,0.5,0.5,0.5,0.015625,0.5078125,0.9453125,0.5,0.5,0.5,0.5
+221,model.layers.31.mlp.gate_proj,tx.31.mlp.gate,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.046875,0.5078125,0.890625,0.5,0.5,0.5,0.5
+222,model.layers.31.mlp.up_proj,tx.31.mlp.up,Linear,weight,"[14336, 4096]",58720256,29360128,0.5,"(128, 16)",112 x 256,28672,0.5,0.5,0.5,0.5,0.5,0.0546875,0.5078125,0.84375,0.5,0.5,0.5,0.5
+223,model.layers.31.mlp.down_proj,tx.31.mlp.down,Linear,weight,"[4096, 14336]",58720256,29360128,0.5,"(128, 16)",32 x 896,28672,0.5,0.5,0.5,0.5,0.5,0.0,0.5390625,1.0,0.5,0.5,0.5,0.5
+224,lm_head,lm_head,Linear,weight,"[128256, 4096]",525336576,525336576,0.0,"(128, 16)",1002 x 256,256512,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2061 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}