Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+tags:
+- merge
+- mergekit
+- lazymergekit
+- deepseek-ai/deepseek-math-7b-rl
+- deepseek-ai/deepseek-math-7b-instruct
+---
+
+# deep-wizard-7B-slerp
+
+deep-wizard-7B-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl)
+* [deepseek-ai/deepseek-math-7b-instruct](https://huggingface.co/deepseek-ai/deepseek-math-7b-instruct)
+
+## 🧩 Configuration
+
+```yaml
+  models:
+    - model: deepseek-ai/deepseek-math-7b-base
+      # no parameters necessary for base model
+    - model: deepseek-ai/deepseek-math-7b-rl
+      parameters:
+        density: 0.5
+        weight: 0.7
+    - model: deepseek-ai/deepseek-math-7b-instruct
+      parameters:
+        density: 0.5
+        weight: 0.3
+  merge_method: dare_ties
+  base_model: deepseek-ai/deepseek-math-7b-base
+  parameters:
+    int8_mask: true
+  dtype: bfloat16
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-math-7b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+  models:
+    - model: deepseek-ai/deepseek-math-7b-base
+      # no parameters necessary for base model
+    - model: deepseek-ai/deepseek-math-7b-rl
+      parameters:
+        density: 0.5
+        weight: 0.7
+    - model: deepseek-ai/deepseek-math-7b-instruct
+      parameters:
+        density: 0.5
+        weight: 0.3
+  merge_method: dare_ties
+  base_model: deepseek-ai/deepseek-math-7b-base
+  parameters:
+    int8_mask: true
+  dtype: bfloat16

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1c809af1212f9fe7633e68965f8938c8d3ff5050ec43b2c212e707fb069b6e
+size 1990276000

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8241cd6bc56ec2c2353b5f8065688d9ab892fd5ced295bb8c14f8eb89ec82a1
+size 1990284264

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cad147e6d88319f6bd8aeb77ccabeee0391bb0e0d4ae92d0c7fe1020a66198
+size 1990284256

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b606f7263916c0eebf2a304c01f0c7c31f0e5ff9c5ac7403463707229f75f3
+size 1973464256

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38278c4eac18f48ed48e082f782efcec04cf78a73797c0f15e04449979b2ffc
+size 1990276000

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7ccecf33c46524472ddd8f5ea422e72c691f361e5c6eb8cd82bb19778d4f13
+size 1986063416

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7151d0dfa387d85f32966f983c899e896d40446ca1c4d85919d2b6105e8eab28
+size 1900114936

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 13820731392}, "weight_map": {"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.embed_tokens.weight": "model-00004-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00007.safetensors", "lm_head.weight": "model-00006-of-00007.safetensors", "model.norm.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00007.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}