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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+- Anannta/Qwen-STEM-Specialist-7B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# R1-STEM-Coder-7B
+
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
+* [Anannta/Qwen-STEM-Specialist-7B](https://huggingface.co/Anannta/Qwen-STEM-Specialist-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+merge_method: slerp
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+dtype: bfloat16
+tokenizer_source: base
+models:
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+  - model: Anannta/Qwen-STEM-Specialist-7B
+parameters:
+  t:
+    - filter: "lm_head"
+      value: 0.0
+    - filter: "model.embed_tokens"
+      value: 0.0
+    - value: [0.0, 0.5, 0.5, 0.0]
+
+```

chat_template.jinja

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

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+
+merge_method: slerp
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+dtype: bfloat16
+tokenizer_source: base
+models:
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+  - model: Anannta/Qwen-STEM-Specialist-7B
+parameters:
+  t:
+    - filter: "lm_head"
+      value: 0.0
+    - filter: "model.embed_tokens"
+      value: 0.0
+    - value: [0.0, 0.5, 0.5, 0.0]

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf85d55ec84d492bd957e09813e816a911ce09e4f050abf9f904d02b9a1c6f4
+size 1087134848

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1ce02a60cd62f8792e0f91d0ae0454a223320b3ac7065e2fa53d2c3e2f3672
+size 1087134864

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a60c243697aeae56f26ed8abbe24f09e0a8b3cb5f39a7be5a55745f5ac4f2c7
+size 932241160

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a69768276281a9a9784bdba798e84e26e0efa62c4a5556837a42537dfebd14c
+size 932233912

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7acfdea747b6e65b4ff9e3b89ccf547825d870b62148717aa720c447fcd4746
+size 932233912

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e4f15d3ef442e5bb8427fc61c6d30dd4d16326a727c0969a2dd45b64b04ffd
+size 932233912

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5a73b3f952bd1421df25469db923c25033334411d079d8bde69aa09829dfa0
+size 932233912

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc32ecfefd179638d5bd74d48577b0953995870d8728fd4507cfd1fd637e4c5
+size 932233912

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57d125110cc5de242c148b509bdf6da9f1d65f0ca1ca184655e7f0a1b65eff6
+size 932233904

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76f8cff5d3eaebb3b6b818825ec55a93868fa386b2f01756f7de3f4169fabca
+size 932233912

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963375ffead46bde3d02ed3f1658fc8e49a9ff10f80885c5524f7dc5dedcf854
+size 932233912

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bf746118fde650cdbd08a536118de6e8420cbbd927123d876003ea9f791bc9
+size 932233912

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e11fe96077831c85436ffe3a03789043b4d99730fa867414e169f224c86e19
+size 932233904

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb82c51220bb143ceefa2b7a01d56364f887487989673d3d8d8d0e78eedff535
+size 932233888

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cc92b75364537ed748cf4a236220367f16d02e33a2b8ec1de5a3e6019ce822
+size 932233888

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb0000604a7c2f66845535d88053a7627d92a806867b25e0906804d1124607e
+size 932233872

model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_size": 15225512960,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00016.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
+    "model.norm.weight": "model-00016-of-00016.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322664cdc3082b6eba003af5228a77ca1d7936d402e584ecde8f15d3d98bdb72
+size 11421911

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}