Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+lycosa.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+license: llama3.3
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+library_name: transformers
+tags:
+- not-for-all-audiences
+- nsfw
+- mergekit
+- merge
+
+---
+# L3.3-70B-Lycosa
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+
+An RP merge with a focus on:
+<br>\- model intelligence
+<br>\- removing positive bias
+<br>\- creativity
+
+This model was merged using the sce merge method using deepseek-r1-distill-llama-70b as a base.
+<br>\
+Note: forcing the llama3.3 chat template can sometimes yield better results. The deepseek chat template is the default provided in config.
+
+<img src="https://huggingface.co/divinetaco/L3.3-70B-Lycosa-v0.1/resolve/main/lycosa.png">
+
+### Models Merged
+
+The following models were included in the merge:
+* deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+* Sao10K/70B-L3.3-Cirrus-x1
+* TheDrummer/Nautilus-70B-v0.1
+* Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
+* SicariusSicariiStuff/Negative_LLAMA_70B
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  # Pivot model
+  - model: llama-3.3-70b-instruct
+  # Target models
+  - model: Sao10K/70B-L3.3-Cirrus-x1
+  - model: TheDrummer/Nautilus-70B-v0.1
+  - model: Doctor-Shotgun/L3.3-70B-Magnum-v4-SE
+  - model: SicariusSicariiStuff/Negative_LLAMA_70B
+merge_method: sce
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+parameters:
+  select_topk: 1.0
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,51 @@
+{
+    "_name_or_path": "deepseek-r1-distill-llama-70b",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "eos_token_id": [
+        128001,
+        128008,
+        128009
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 80,
+    "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": "4.47.1",
+    "use_cache": true,
+    "vocab_size": 128256,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.7",
+        "bits": 6.5,
+        "head_bits": 8,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

fusechat-sce.yml

@@ -0,0 +1,13 @@
+models:
+  # Pivot model
+  - model: llama-3.3-70b-instruct
+  # Target models
+  - model: sao10k-70b-l3.3-cirrus-x1
+  - model: Nautilus-70B-v0.1
+  - model: sicariussicariistuff-negative-llama-3.3-70b
+  - model: doctor-shotgun-magnum-v4-se-70b
+merge_method: sce
+base_model: deepseek-r1-distill-llama-70b
+parameters:
+  select_topk: 1.0
+dtype: bfloat16

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 141107412992}, "weight_map": {"lm_head.weight": "model-00001-of-00030.safetensors", "model.embed_tokens.weight": "model-00001-of-00030.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00030.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00030.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00030.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.input_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.norm.weight": "model-00030-of-00030.safetensors"}}

output-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136cf6188387f8e2f4bcb2dae8f946c5c8da88d9fabfd56ba6bf4d8539e4d191
+size 8515299748

output-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92ad02116051ad98be2243cd0c0109153cfa862f19188fc76ce5d1ab5fba568
+size 8405372956

output-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:541cef28c3821f128b0dae1f06b2bc719ef25c25bcf3c94e8342250a0b4eec90
+size 8511674828

output-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734e7d776ce7e9f9439032f2649790b3bb9f29c46f536e252aafceb7ca0c7275
+size 8432333724

output-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4704e10ae67a4182db8e32443c427b850b30e3c232470dd84e1785025ac6cbb9
+size 8556015448

output-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf0e9d1f486e2c39ada4b213b1b45aab26fe23d35df5aeb7e86e42f6bcf5006
+size 8557607428

output-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26146f9ec7b0d55c333fc9f08ae51974b592d80b829288fb409322523ee48cb2
+size 7673164368

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% 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｜>'}}{% endif %}"
+}