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 +1,58 @@
+ ---
+language:
+- en
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tags:
+- chat
+library_name: transformers
+license: mit
+---
+
+# Stepfun-Prover-Preview-7B
+
+**Stepfun-Prover-Preview-7B** is a theorem proving model developed by Stepfun Team. It can iteratively refine the proof sketch via interacting with Lean4, and achieve 66.0% accuracy with Pass@1 on MiniF2F-test. Advanced usage examples can be seen in [github](https://github.com/stepfun-ai/Stepfun-Prover-Preview).
+
+# Quick Start with vLLM
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_name = "Stepfun/Stepfun-Prover-Preview-7B"
+model = LLM(
+    model=model_name,
+    tensor_parallel_size=4,
+    )
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+formal_problem = """
+import Mathlib
+
+theorem test_theorem (x y z : ℝ) (hx : 0 < x) (hy : 0 < y) (hz : 0 < z) :
+    (x^2 - z^2) / (y + z) + (y^2 - x^2) / (z + x) + (z^2 - y^2) / (x + y) ≥ 0 := by
+""".strip()
+
+system_prompt = "You will be given an unsolved Lean 4 problem. Think carefully and work towards a solution. At any point, you may use the Lean 4 REPL to check your progress by enclosing your partial solution between <sketch> and </sketch>. The REPL feedback will be provided between <REPL> and </REPL>. Continue this process as needed until you arrive at a complete and correct solution."
+
+user_prompt = f"```lean4\n{formal_problem}\n```"
+
+dialog = [
+  {"role": "system", "content": system_prompt},
+  {"role": "user", "content": user_prompt}
+] 
+
+prompt = tokenizer.apply_chat_template(dialog, tokenize=False, add_generation_prompt=True)
+
+sampling_params = SamplingParams(
+    temperature=0.999,
+    top_p=0.95,
+    top_k=-1,
+    max_tokens=16384,
+    stop_token_ids=[151643, 151666], # <｜end▁of▁sentence｜>, </sketch>
+    include_stop_str_in_output=True,
+)
+
+output = model.generate(prompt, sampling_params=sampling_params)
+output_text = output[0].outputs[0].text
+print(output_text)
+```

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 +1,28 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.0",
+    "use_cache": true,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

generate_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_p": 0.95,
+  "transformers_version": "4.54.0"
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3aeb47ceecf799a275ab4ef703dff6f93c32b6cc76d8c4456c6af072b850c84
+size 4253782776

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad13314f7acb45e80dd89524f0e655f7207cdff6db6c84f8bf821af0eb4c9ab4
+size 4195052616

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b95d237b2a1c92d8d7fe34e0f6183137f40dd572ba3c97f58f0d70897bcf94
+size 4195052632

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4406405f063a122734d75e39689906626b3600152477e2ca182f99b137d7d88
+size 2587383656

model.safetensors.index.json

@@ -0,0 +1,344 @@
+{
+    "metadata": {},
+    "weight_map": {
+        "model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00001.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00001.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00001.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004.safetensors",
+        "model.embed_tokens.weight": "model-00004.safetensors",
+        "model.norm.weight": "model-00004.safetensors",
+        "lm_head.weight": "model-00004.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eedbf07704361ce2fa255b6fa6d891bb8455d813cd74d749de0b4497b4702c5
+size 11423149

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<sketch>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</sketch>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 163840,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}