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 +1,45 @@
+---
+tags: [eoq, quantized, entropy-coding]
+base_model: Qwen/Qwen2.5-3B
+license: apache-2.0
+---
+
+# Qwen2.5-3B EOQ Q5
+
+Quantized with **EOQ (Entropy-Optimal Quantization)**: absmax Q5 + rANS entropy coding.
+
+## Benchmark (RTX 6000 Blackwell 96GB VRAM)
+
+| Format | Size | PPL (WikiText-2) | tok/s |
+|--------|------|------------------|-------|
+| FP16 | 6172 MB | 6.54 | 96.9 |
+| GGUF Q4_K_M | 2020 MB | ~ref | ~ref |
+| **EOQ Q5** | **1724 MB** | **6.77** | **97.1** |
+
+14.6% smaller than GGUF Q4_K_M
+
+PPL degradation vs FP16: +0.23 points. Zero inference overhead.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained("caiovicentino1/Qwen2.5-3B-EOQ-Q5", dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("caiovicentino1/Qwen2.5-3B-EOQ-Q5")
+
+inputs = tokenizer("Hello!", return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=100)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+## What is EOQ?
+
+EOQ combines block-wise absmax quantization with rANS entropy coding.
+Quantized weights have Shannon entropy below their bit width.
+rANS removes this redundancy losslessly, saving 10-18% over raw quantization.
+
+## GitHub
+
+https://github.com/caiovicentino/eoq-quantization

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0.dev0",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c22cf59494cde11f59fffd634d88aac6f607611448ba37ce2132191f5cdd8f
+size 5356048400

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a7abcc1f5b7e529b108c257e35461321dd17565458ae37f93aedbb4c371b2c
+size 815878112

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"total_size": 6171877376}, "weight_map": {"model.embed_tokens.weight": "model-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.1.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.2.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.3.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.4.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.5.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.6.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.7.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.8.self_attn.v_proj.weight": "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.q_proj.bias": "model-00001.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.9.self_attn.v_proj.weight": "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-00001.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.9.input_layernorm.weight": "model-00001.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.10.input_layernorm.weight": "model-00001.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.11.input_layernorm.weight": "model-00001.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.12.input_layernorm.weight": "model-00001.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.13.input_layernorm.weight": "model-00001.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.14.input_layernorm.weight": "model-00001.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.15.input_layernorm.weight": "model-00001.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.16.input_layernorm.weight": "model-00001.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.17.input_layernorm.weight": "model-00001.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.18.input_layernorm.weight": "model-00001.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.19.input_layernorm.weight": "model-00001.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.20.input_layernorm.weight": "model-00001.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.21.input_layernorm.weight": "model-00001.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.22.input_layernorm.weight": "model-00001.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.23.input_layernorm.weight": "model-00001.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.24.input_layernorm.weight": "model-00001.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.25.input_layernorm.weight": "model-00001.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.26.input_layernorm.weight": "model-00001.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.27.input_layernorm.weight": "model-00001.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.28.input_layernorm.weight": "model-00001.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.29.input_layernorm.weight": "model-00001.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00001.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00001.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00001.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00002.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00002.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00002.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00002.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00002.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00002.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00002.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.33.input_layernorm.weight": "model-00002.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00002.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00002.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00002.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00002.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00002.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00002.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00002.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.35.input_layernorm.weight": "model-00002.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002.safetensors", "model.norm.weight": "model-00002.safetensors"}}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}