Upload folder using huggingface_hub

README.md

@@ -0,0 +1,50 @@
+---
+base_model:
+- deepseek-ai/deepseek-math-7b-rl
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: linear
+parameters:
+  weight: 1.0
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [1, 10]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [5, 15]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [10, 20]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [15, 25]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [20, 30]
+dtype: float16
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "deepseek-ai/deepseek-math-7b-rl",
+  "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",
+  "moe_intermediate_size": 11008,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 49,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 102400
+}

mergekit_config.yml

@@ -0,0 +1,20 @@
+merge_method: linear
+parameters:
+  weight: 1.0
+slices:
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [1, 10]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [5, 15]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [10, 20]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [15, 25]
+  - sources:
+      - model: deepseek-ai/deepseek-math-7b-rl
+        layer_range: [20, 30]
+dtype: float16

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80eef9e4ed56f78197485148bcf43c57a220bda5cd8a90faa06bc9c9c6327679
+size 9991224328

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24adaed7a732cd7ca57a70feb1e2d3f2b44020b6648aa5d87dded2d55de7f70c
+size 9968164104

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8976d5b82b1474c084ae116f02bb8af71f0bab5eb4d8e4c8dbccd9086f7051
+size 1551961936

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 21511299072}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.norm.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.embed_tokens.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.47.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00003.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 +1,32 @@
+{
+  "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｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
+  "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
+}