Add files using upload-large-folder tool

.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
+Qwen3-8B/ll_4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Qwen3-8B/ll_4bit/README.md

@@ -0,0 +1,7 @@
+# Quantized Model Checkpoint
+
+**Base model:** unknown
+
+**Average bitwidth:** unknown
+
+See `quantization_config.txt` for full configuration details.

Qwen3-8B/ll_4bit/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

Qwen3-8B/ll_4bit/config.json

@@ -0,0 +1,71 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

Qwen3-8B/ll_4bit/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.3.0"
+}

Qwen3-8B/ll_4bit/humming_online_quant_config.json

@@ -0,0 +1,5 @@
+{
+  "quant_method": "gptq",
+  "bits": 4,
+  "group_size": 128
+}

Qwen3-8B/ll_4bit/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a198d1c3eae2ad7b97fececf22213c03d0c53d9f9a0809ca3d8d62e9d5249950
+size 16381516808

Qwen3-8B/ll_4bit/quantization_config.txt

@@ -0,0 +1,252 @@
+model.layers.23.self_attn.k_proj: 4
+model.layers.22.self_attn.o_proj: 4
+model.layers.4.self_attn.o_proj: 4
+model.layers.1.mlp.down_proj: 4
+model.layers.11.mlp.up_proj: 4
+model.layers.5.self_attn.k_proj: 4
+model.layers.14.self_attn.q_proj: 4
+model.layers.17.mlp.down_proj: 4
+model.layers.33.mlp.gate_proj: 4
+model.layers.5.self_attn.v_proj: 4
+model.layers.23.self_attn.v_proj: 4
+model.layers.27.mlp.gate_proj: 4
+model.layers.2.mlp.up_proj: 4
+model.layers.15.self_attn.q_proj: 4
+model.layers.23.self_attn.o_proj: 4
+model.layers.21.mlp.up_proj: 4
+model.layers.22.self_attn.k_proj: 4
+model.layers.4.mlp.down_proj: 4
+model.layers.4.self_attn.k_proj: 4
+model.layers.5.self_attn.o_proj: 4
+model.layers.31.mlp.up_proj: 4
+model.layers.4.self_attn.v_proj: 4
+model.layers.22.self_attn.v_proj: 4
+model.layers.22.mlp.gate_proj: 4
+model.layers.8.mlp.gate_proj: 4
+model.layers.12.mlp.down_proj: 4
+model.layers.7.mlp.gate_proj: 4
+model.layers.35.self_attn.o_proj: 4
+model.layers.21.self_attn.v_proj: 4
+model.layers.34.self_attn.k_proj: 4
+model.layers.7.self_attn.v_proj: 4
+model.layers.7.self_attn.k_proj: 4
+model.layers.6.self_attn.o_proj: 4
+model.layers.34.self_attn.v_proj: 4
+model.layers.20.self_attn.o_proj: 4
+model.layers.13.mlp.up_proj: 4
+model.layers.21.self_attn.k_proj: 4
+model.layers.35.mlp.down_proj: 4
+model.layers.28.self_attn.q_proj: 4
+model.layers.11.mlp.gate_proj: 4
+model.layers.16.self_attn.q_proj: 4
+model.layers.21.mlp.down_proj: 4
+model.layers.35.self_attn.k_proj: 4
+model.layers.33.mlp.up_proj: 4
+model.layers.20.self_attn.v_proj: 4
+model.layers.34.self_attn.o_proj: 4
+model.layers.6.self_attn.v_proj: 4
+model.layers.28.mlp.gate_proj: 4
+model.layers.2.mlp.gate_proj: 4
+model.layers.18.mlp.down_proj: 4
+model.layers.17.self_attn.q_proj: 4
+model.layers.0.mlp.up_proj: 4
+model.layers.24.mlp.down_proj: 4
+model.layers.23.mlp.up_proj: 4
+model.layers.7.self_attn.o_proj: 4
+model.layers.6.self_attn.k_proj: 4
+model.layers.29.self_attn.q_proj: 4
+model.layers.20.self_attn.k_proj: 4
+model.layers.30.mlp.down_proj: 4
+model.layers.14.mlp.gate_proj: 4
+model.layers.21.self_attn.o_proj: 4
+model.layers.35.self_attn.v_proj: 4
+model.layers.6.mlp.up_proj: 4
+model.layers.9.self_attn.q_proj: 4
+model.layers.0.self_attn.k_proj: 4
+model.layers.9.mlp.up_proj: 4
+model.layers.1.self_attn.o_proj: 4
+model.layers.33.self_attn.v_proj: 4
+model.layers.27.self_attn.o_proj: 4
+model.layers.26.self_attn.k_proj: 4
+model.layers.19.self_attn.o_proj: 4
+model.layers.0.mlp.gate_proj: 4
+model.layers.11.self_attn.q_proj: 4
+model.layers.18.self_attn.k_proj: 4
+model.layers.25.mlp.up_proj: 4
+model.layers.26.mlp.down_proj: 4
+model.layers.18.self_attn.v_proj: 4
+model.layers.35.mlp.up_proj: 4
+model.layers.32.self_attn.o_proj: 4
+model.layers.26.self_attn.v_proj: 4
+model.layers.33.self_attn.k_proj: 4
+model.layers.32.mlp.down_proj: 4
+model.layers.16.mlp.gate_proj: 4
+model.layers.0.self_attn.v_proj: 4
+model.layers.15.mlp.up_proj: 4
+model.layers.19.self_attn.k_proj: 4
+model.layers.10.self_attn.q_proj: 4
+model.layers.5.mlp.gate_proj: 4
+model.layers.18.self_attn.o_proj: 4
+model.layers.0.self_attn.o_proj: 4
+model.layers.1.self_attn.k_proj: 4
+model.layers.8.self_attn.q_proj: 4
+model.layers.27.self_attn.k_proj: 4
+model.layers.26.self_attn.o_proj: 4
+model.layers.32.self_attn.v_proj: 4
+model.layers.9.mlp.down_proj: 4
+model.layers.32.self_attn.k_proj: 4
+model.layers.13.mlp.gate_proj: 4
+model.layers.27.self_attn.v_proj: 4
+model.layers.33.self_attn.o_proj: 4
+model.layers.1.self_attn.v_proj: 4
+model.layers.23.mlp.down_proj: 4
+model.layers.19.self_attn.v_proj: 4
+model.layers.2.self_attn.v_proj: 4
+model.layers.6.mlp.down_proj: 4
+model.layers.31.self_attn.k_proj: 4
+model.layers.24.self_attn.v_proj: 4
+model.layers.30.self_attn.o_proj: 4
+model.layers.24.self_attn.k_proj: 4
+model.layers.4.mlp.up_proj: 4
+model.layers.25.self_attn.o_proj: 4
+model.layers.31.self_attn.v_proj: 4
+model.layers.20.mlp.gate_proj: 4
+model.layers.3.self_attn.o_proj: 4
+model.layers.2.self_attn.k_proj: 4
+model.layers.10.mlp.down_proj: 4
+model.layers.34.mlp.gate_proj: 4
+model.layers.13.self_attn.q_proj: 4
+model.layers.28.mlp.up_proj: 4
+model.layers.27.mlp.up_proj: 4
+model.layers.3.mlp.down_proj: 4
+model.layers.3.self_attn.v_proj: 4
+model.layers.19.mlp.gate_proj: 4
+model.layers.31.self_attn.o_proj: 4
+model.layers.25.self_attn.v_proj: 4
+model.layers.30.self_attn.k_proj: 4
+model.layers.29.mlp.down_proj: 4
+model.layers.18.mlp.up_proj: 4
+model.layers.15.mlp.down_proj: 4
+model.layers.17.mlp.up_proj: 4
+model.layers.31.mlp.gate_proj: 4
+model.layers.12.self_attn.q_proj: 4
+model.layers.30.self_attn.v_proj: 4
+model.layers.24.self_attn.o_proj: 4
+model.layers.25.self_attn.k_proj: 4
+model.layers.25.mlp.gate_proj: 4
+model.layers.3.self_attn.k_proj: 4
+model.layers.2.self_attn.o_proj: 4
+model.layers.2.mlp.down_proj: 4
+model.layers.16.self_attn.o_proj: 4
+model.layers.18.mlp.gate_proj: 4
+model.layers.17.self_attn.k_proj: 4
+model.layers.6.self_attn.q_proj: 4
+model.layers.28.mlp.down_proj: 4
+model.layers.28.self_attn.o_proj: 4
+model.layers.20.self_attn.q_proj: 4
+model.layers.29.self_attn.k_proj: 4
+model.layers.29.self_attn.v_proj: 4
+model.layers.14.mlp.down_proj: 4
+model.layers.35.self_attn.q_proj: 4
+model.layers.30.mlp.gate_proj: 4
+model.layers.24.mlp.gate_proj: 4
+model.layers.14.mlp.up_proj: 4
+model.layers.17.self_attn.v_proj: 4
+model.layers.7.self_attn.q_proj: 4
+model.layers.28.self_attn.k_proj: 4
+model.layers.21.self_attn.q_proj: 4
+model.layers.29.self_attn.o_proj: 4
+model.layers.7.mlp.down_proj: 4
+model.layers.16.self_attn.k_proj: 4
+model.layers.17.self_attn.o_proj: 4
+model.layers.34.mlp.up_proj: 4
+model.layers.21.mlp.gate_proj: 4
+model.layers.16.self_attn.v_proj: 4
+model.layers.24.mlp.up_proj: 4
+model.layers.34.self_attn.q_proj: 4
+model.layers.8.mlp.up_proj: 4
+model.layers.11.mlp.down_proj: 4
+model.layers.7.mlp.up_proj: 4
+model.layers.35.mlp.gate_proj: 4
+model.layers.28.self_attn.v_proj: 4
+model.layers.4.mlp.gate_proj: 4
+model.layers.16.mlp.up_proj: 4
+model.layers.15.self_attn.v_proj: 4
+model.layers.19.mlp.up_proj: 4
+model.layers.8.mlp.down_proj: 4
+model.layers.12.mlp.gate_proj: 4
+model.layers.15.self_attn.k_proj: 4
+model.layers.14.self_attn.o_proj: 4
+model.layers.22.self_attn.q_proj: 4
+model.layers.22.mlp.down_proj: 4
+model.layers.4.self_attn.q_proj: 4
+model.layers.14.self_attn.v_proj: 4
+model.layers.26.mlp.up_proj: 4
+model.layers.29.mlp.up_proj: 4
+model.layers.5.mlp.up_proj: 4
+model.layers.1.mlp.gate_proj: 4
+model.layers.27.mlp.down_proj: 4
+model.layers.23.self_attn.q_proj: 4
+model.layers.5.self_attn.q_proj: 4
+model.layers.33.mlp.down_proj: 4
+model.layers.17.mlp.gate_proj: 4
+model.layers.15.self_attn.o_proj: 4
+model.layers.14.self_attn.k_proj: 4
+model.layers.12.self_attn.k_proj: 4
+model.layers.13.self_attn.o_proj: 4
+model.layers.29.mlp.gate_proj: 4
+model.layers.25.self_attn.q_proj: 4
+model.layers.30.mlp.up_proj: 4
+model.layers.3.mlp.gate_proj: 4
+model.layers.19.mlp.down_proj: 4
+model.layers.3.self_attn.q_proj: 4
+model.layers.20.mlp.up_proj: 4
+model.layers.30.self_attn.q_proj: 4
+model.layers.25.mlp.down_proj: 4
+model.layers.12.self_attn.v_proj: 4
+model.layers.3.mlp.up_proj: 4
+model.layers.31.mlp.down_proj: 4
+model.layers.15.mlp.gate_proj: 4
+model.layers.24.self_attn.q_proj: 4
+model.layers.2.self_attn.q_proj: 4
+model.layers.6.mlp.gate_proj: 4
+model.layers.12.self_attn.o_proj: 4
+model.layers.13.self_attn.k_proj: 4
+model.layers.13.self_attn.v_proj: 4
+model.layers.34.mlp.down_proj: 4
+model.layers.10.mlp.gate_proj: 4
+model.layers.10.mlp.up_proj: 4
+model.layers.20.mlp.down_proj: 4
+model.layers.31.self_attn.q_proj: 4
+model.layers.22.mlp.up_proj: 4
+model.layers.32.self_attn.q_proj: 4
+model.layers.8.self_attn.v_proj: 4
+model.layers.5.mlp.down_proj: 4
+model.layers.10.self_attn.v_proj: 4
+model.layers.1.mlp.up_proj: 4
+model.layers.11.self_attn.o_proj: 4
+model.layers.10.self_attn.k_proj: 4
+model.layers.19.self_attn.q_proj: 4
+model.layers.23.mlp.gate_proj: 4
+model.layers.8.self_attn.k_proj: 4
+model.layers.32.mlp.up_proj: 4
+model.layers.1.self_attn.q_proj: 4
+model.layers.9.self_attn.o_proj: 4
+model.layers.9.mlp.gate_proj: 4
+model.layers.13.mlp.down_proj: 4
+model.layers.27.self_attn.q_proj: 4
+model.layers.0.mlp.down_proj: 4
+model.layers.11.self_attn.v_proj: 4
+model.layers.33.self_attn.q_proj: 4
+model.layers.9.self_attn.v_proj: 4
+model.layers.12.mlp.up_proj: 4
+model.layers.8.self_attn.o_proj: 4
+model.layers.0.self_attn.q_proj: 4
+model.layers.9.self_attn.k_proj: 4
+model.layers.26.self_attn.q_proj: 4
+model.layers.16.mlp.down_proj: 4
+model.layers.32.mlp.gate_proj: 4
+model.layers.18.self_attn.q_proj: 4
+model.layers.11.self_attn.k_proj: 4
+model.layers.10.self_attn.o_proj: 4
+model.layers.26.mlp.gate_proj: 4

Qwen3-8B/ll_4bit/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

Qwen3-8B/ll_4bit/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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
+}