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
+model.gguf filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.DS_Store

README.md

@@ -1,3 +1,21 @@
----
-license: mit
----
+---
+pipeline_tag: text-generation
+base_model_relation: quantized
+base_model: Qwen/Qwen3-4B-Instruct-2507
+library_name: transformers
+license: mit
+license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE
+tags:
+  - qwen
+  - qwen3
+  - unsloth
+  - gguf
+---
+
+# Qwen3 4B Instruct 2507 by Qwen
+
+**Model creator:** [Qwen](https://huggingface.co/Qwen)
+**Original model**: [Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+**GGUF quantization:** provided by [unsloth](https://huggingface.co/unsloth)
+
+[![Unsloth Logo](https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png)](https://github.com/unslothai/unsloth/)

config.json

@@ -0,0 +1,49 @@
+{
+  "format": "gguf",
+  "quantization": "IQ2_XXS/Q4_K_M",
+  "parameters": "4.02 B",
+  "architecture": "qwen3",
+  "size": "2.32 GiB",
+  "gguf": {
+    "general.architecture": "qwen3",
+    "general.base_model.0.name": "Qwen3 4B Instruct 2507",
+    "general.base_model.0.organization": "Qwen",
+    "general.base_model.0.repo_url": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507",
+    "general.base_model.0.version": "2507",
+    "general.base_model.count": "1",
+    "general.basename": "Qwen3-4B-Instruct-2507",
+    "general.file_type": "15",
+    "general.finetune": "Instruct",
+    "general.license": "apache-2.0",
+    "general.license.link": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE",
+    "general.name": "Qwen3-4B-Instruct-2507",
+    "general.quantization_version": "2",
+    "general.quantized_by": "Unsloth",
+    "general.repo_url": "https://huggingface.co/unsloth",
+    "general.size_label": "4B",
+    "general.tags": "unsloth, text-generation",
+    "general.type": "model",
+    "general.version": "2507",
+    "quantize.imatrix.chunks_count": "79",
+    "quantize.imatrix.dataset": "unsloth_calibration_Qwen3-4B-Instruct-2507.txt",
+    "quantize.imatrix.entries_count": "252",
+    "quantize.imatrix.file": "Qwen3-4B-Instruct-2507-GGUF/imatrix_unsloth.gguf",
+    "qwen3.attention.head_count": "32",
+    "qwen3.attention.head_count_kv": "8",
+    "qwen3.attention.key_length": "128",
+    "qwen3.attention.layer_norm_rms_epsilon": "0.000001",
+    "qwen3.attention.value_length": "128",
+    "qwen3.block_count": "36",
+    "qwen3.context_length": "262144",
+    "qwen3.embedding_length": "2560",
+    "qwen3.feed_forward_length": "9728",
+    "qwen3.rope.freq_base": "5000000.000000",
+    "tokenizer.chat_template": "{%- if tools %}\n    {{- '\u003c|im_start|\u003esystem\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within \u003ctools\u003e\u003c/tools\u003e XML tags:\\n\u003ctools\u003e\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n\u003c/tools\u003e\\n\\nFor each function call, return a json object with function name and arguments within \u003ctool_call\u003e\u003c/tool_call\u003e XML tags:\\n\u003ctool_call\u003e\\n{\\\"name\\\": \u003cfunction-name\u003e, \\\"arguments\\\": \u003cargs-json-object\u003e}\\n\u003c/tool_call\u003e\u003c|im_end|\u003e\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '\u003c|im_start|\u003esystem\\n' + messages[0].content + '\u003c|im_end|\u003e\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('\u003ctool_response\u003e') and message.content.endswith('\u003c/tool_response\u003e')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '\u003c|im_start|\u003e' + message.role + '\\n' + content + '\u003c|im_end|\u003e' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '\u003c/think\u003e' in content %}\n                {%- set reasoning_content = ((content.split('\u003c/think\u003e')|first).rstrip('\\n').split('\u003cthink\u003e')|last).lstrip('\\n') %}\n                {%- set content = (content.split('\u003c/think\u003e')|last).lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 \u003e ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '\u003c|im_start|\u003e' + message.role + '\\n\u003cthink\u003e\\n' + reasoning_content.strip('\\n') + '\\n\u003c/think\u003e\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '\u003c|im_start|\u003e' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '\u003c|im_start|\u003e' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '\u003ctool_call\u003e\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n\u003c/tool_call\u003e' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\u003c|im_end|\u003e\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '\u003c|im_start|\u003euser' }}\n        {%- endif %}\n        {{- '\\n\u003ctool_response\u003e\\n' }}\n        {{- content }}\n        {{- '\\n\u003c/tool_response\u003e' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '\u003c|im_end|\u003e\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '\u003c|im_start|\u003eassistant\\n' }}\n{%- endif %}",
+    "tokenizer.ggml.add_bos_token": "false",
+    "tokenizer.ggml.eos_token_id": "151645",
+    "tokenizer.ggml.model": "gpt2",
+    "tokenizer.ggml.padding_token_id": "151654",
+    "tokenizer.ggml.pre": "qwen2"
+  },
+  "context_size": 6144
+}

model.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3605803b982cb64aead44f6c1b2ae36e3acdb41d8e46c8a94c6533bc4c67e597
+size 2497281120