test

chat_template.jinja

@@ -0,0 +1,37 @@
+[gMASK]<sop>{% for item in messages %}{% if item['tools'] is defined %}<|system|>
+你是一个名为 ChatGLM 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。
+
+# 可用工具{% set tools = item['tools'] %}{% for tool in tools %}{% if tool['type'] == 'function' %}
+
+## {{ tool['function']['name'] }}
+
+{{ tool['function'] | tojson(indent=4) }}
+在调用上述函数时，请使用 Json 格式表示调用的参数。{% elif tool['type'] == 'python' %}
+
+## python
+
+当你向 `python` 发送包含 Python 代码的消息时，该代码将会在一个有状态的 Jupyter notebook 环境中执行。
+`python` 返回代码执行的输出，或在执行 60 秒后返回超时。
+`/mnt/data` 将会持久化存储你的文件。在此会话中，`python` 无法访问互联网。不要使用 `python` 进行任何网络请求或者在线 API 调用，这些在线内容的访问将不会成功。{% elif tool['type'] == 'simple_browser' %}
+
+## simple_browser
+
+你可以使用 `simple_browser` 工具。该工具支持以下函数：
+`search(query: str, recency_days: int)`：使用搜索引擎进行查询并显示结果，可以使用 `recency_days` 参数控制搜索内容的时效性。
+`mclick(ids: list[int])`：获取一系列指定 id 的页面内容。每次调用时，须选择3-10个页面。选择多个角度的页面，同时尽可能选择可信任的信息来源。考虑到部分页面是无法加载的，你也可以多打开一些可能有用的页面而不用担心内容过多。
+`open_url(url: str)`：打开指定的 URL。
+
+使用 `【{引用 id}†{引用文本}】` 来引用内容。
+
+操作步骤：1. 使用 `search` 来获得信息列表; 2. 使用 `mclick` 来获取指定 ID 页面的内容; 3. 根据获得的内容进行回复。在回复中应当引用信息来源。
+ 如果用户提供了 URL，也可以用 `open_url` 直接打开页面。
+如果初次搜索结果没有找到合适的信息，也可以再次使用 `search` 进行搜索。{% elif tool['type'] == 'cogview' %}
+
+## cogview
+
+如果用户的请求中包含了对图像的描述，你可以使用 `cogview` 来生成图像并展示给用户。你需要向 `cogview` 发送图像描述，规则：
+- 发送给 `cogview` 的消息必须使用英语。用户的中文描述必须完全翻译为英语。
+- 应当尽可能详细地描述图像生成的需求，需求描述约 100 英文单词。
+- 保持用户原始描述的意图。不要虚构内容或者没见过的人物。
+- 如无特殊说明，所在地为中国，持有中国立场并遵循中国社会主义价值观。{% endif %}{% endfor %}{% endif %}{% if item['content'] %}<|{{ item['role'] }}|>{{ item['metadata'] }}
+{{ item['content'] }}{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "use_cache": true,
+  "vocab_size": 151552
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151329,
+    151336,
+    151338
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.52.0.dev0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bb859bc5a05a47f9838e89b9d969041a735854de465609bf33d72e30f6777c0
+size 4964110224

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f8c79bb84c4d188e60f417db385a9ce615ee2880b23488738b022e7327d806
+size 4951627112

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a68533584ffa87e714b59c572041263d7f0e7bd9a204b0ee01a8b88c556d45e
+size 4750251160

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4281beea6f7f54b65991046bcfce14f0a32bb8e89ac9de83d4453d4342178b30
+size 4467185280

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd7d6ede77d4c9ab71f4e5249d2fa163cd7ecefe71c0978dd59df86d2a7100f
+size 4957918856

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1cd2ab850c7009d3e3ed671fffd7e1dab6e419b22a26c914efa238a5495960
+size 4951627160

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a296d714fe1d2d27e0c54aa6c88fd05a9e7559a1ca49d9e3dd322eb543c6b5
+size 4750251184

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff9bf71d4a8f778e87e6bc3eb5d47b8a45e2dee0536fcb2e64362f10d0ed9d2
+size 4467185280

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e38028a7f6803c43dc38ebdbf5c23dfc07aa1188b4b23207b039e16fee1ed9f
+size 4957918856

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab821ac45c81a6553f195a7d1a1d5b611c37534d267c2e990113c1ce0dbc820
+size 4951627160

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a69ba91c0f481c2aa140018815659b6d8f0c838c92344fd4ce8f9b323e0ea16
+size 4750251184

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673742270f6323b6147e7a14bb6cfeca1b7db5a5c66758f5f523889bfbf2b7c9
+size 4467185280

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5c2cce846f6311edff754511628f287b791dd5ec1e70d1f9ed4a1c21773b89
+size 4957918856

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc4e39b8fe82229551af7c8a82d586f47f487645f553085c44d1806f97855be
+size 2787177488

model.safetensors.index.json

@@ -0,0 +1,620 @@
+{
+  "metadata": {
+    "total_size": 65132163072
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}