Upload ssgr_wanda_7B_sparse50

.gitattributes

@@ -42,3 +42,4 @@ c4_wanda_7B_sparse50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ssgr_wanda_15B_sparse40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ssgr_wanda_15B_sparse50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 ssgr_wanda_7B_sparse40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+ssgr_wanda_7B_sparse50/tokenizer.json filter=lfs diff=lfs merge=lfs -text

ssgr_wanda_7B_sparse50/chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

ssgr_wanda_7B_sparse50/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

ssgr_wanda_7B_sparse50/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2416e388a891683f3cfcafc7dd97b65fda617acabd6143a72459dd87446cb6bd
+size 4877660776

ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6e6f931d19f8d4fbd0d549f0fb91b6914c1417a835b9454237c0574827b707
+size 4932751008

ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f428c30387efadd84b79dd36f911b3033afb22fdd2818433c7b6605d2c5000df
+size 4330865200

ssgr_wanda_7B_sparse50/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784693f9ab4fdb1922b97f1f63b376b4405d1c07abdee98fb6320929396ccc04
+size 1089994880

ssgr_wanda_7B_sparse50/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_parameters": 7615616512, "total_size": 15231233024}, "weight_map": {"lm_head.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00004-of-00004.safetensors", "model.embed_tokens.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.18.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.bias": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00002-of-00004.safetensors", "model.norm.weight": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/model-00003-of-00004.safetensors"}}

ssgr_wanda_7B_sparse50/pairs_annotated.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a268c870e9b23883c19e58cf7ad834b895359b3e2046cd3130895b484d7fcb07
+size 12333855

ssgr_wanda_7B_sparse50/pairs_cache.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58509f3203ff3b35fe2d149415b950807c97dfb4270994499e5e06be68a06cbe
+size 12333855

ssgr_wanda_7B_sparse50/run_config.json

@@ -0,0 +1,48 @@
+{
+  "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "dtype": "bfloat16",
+  "device": "cuda",
+  "dataset": "open-r1/OpenR1-Math-220k",
+  "dataset_config": null,
+  "dataset_split": "train",
+  "problem_col": "problem",
+  "answer_col": "answer",
+  "task_type": "math",
+  "max_problems": 2000,
+  "dataset_offset": 0,
+  "min_rating": null,
+  "max_rating": null,
+  "n_pairs": 32,
+  "n_rollouts": 16,
+  "temperature": 0.8,
+  "max_new_tokens": 32768,
+  "gen_batch_size": 4,
+  "difficulty_lo": 0.2,
+  "difficulty_hi": 0.8,
+  "near_miss_ratio": 0.5,
+  "max_resample": 2,
+  "beta": 2.0,
+  "gamma": 0.5,
+  "eps": 0.1,
+  "min_seg_tokens": 5,
+  "reweight_from_annotated": false,
+  "score_norm": "softmax",
+  "uniform_span_weights": false,
+  "ssgr_min_len_pct": 25.0,
+  "ssgr_max_len_pct": 75.0,
+  "sparsity": 0.5,
+  "scope": "all",
+  "memory_limit_gb": 35.0,
+  "prunen": 0,
+  "prunem": 0,
+  "backend": "wanda",
+  "alps_rho": 0.1,
+  "alps_max_iter": 300,
+  "condition": "ssgr",
+  "output_dir": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50",
+  "pairs_cache": "/mnt/data/vhoangth2/repos/OBC/models/ssgr_wanda_7B_sparse50/pairs_cache.pkl",
+  "annotated_cache": null,
+  "save_rollouts": false,
+  "store_stop_logits": false,
+  "verbose_rollouts": false
+}

ssgr_wanda_7B_sparse50/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ssgr_wanda_7B_sparse50/summary.json

@@ -0,0 +1,9 @@
+{
+  "condition": "ssgr",
+  "sparsity_target": 0.5,
+  "sparsity_realised": 0.4641965699598504,
+  "n_pairs": 39,
+  "beta": 2.0,
+  "gamma": 0.5,
+  "model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
+}

ssgr_wanda_7B_sparse50/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

ssgr_wanda_7B_sparse50/tokenizer_config.json

@@ -0,0 +1,194 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}