Duplicate from TeichAI/Qwen3-14B-Gemini-3-Pro-Preview-High-Reasoning-Distill-GGUF

.gitattributes

@@ -0,0 +1,43 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+qwen3-14b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-14b.F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-14B-Gemini-3-Pro-Preview-Distill.q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,59 @@
+
+FROM qwen3-14b.Q8_0.gguf
+TEMPLATE """{{- if .Messages }}
+{{- if or .System .Tools }}<|im_start|>system
+{{- if .System }}
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+{{- end }}<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+{{ if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}<tool_call>
+{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{ end }}</tool_call>
+{{- end }}{{ if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<|im_start|>"
+PARAMETER temperature 0.6
+PARAMETER min_p 0.0
+PARAMETER top_k 20
+PARAMETER top_p 0.95
+PARAMETER repeat_penalty 1

Qwen3-14B-Gemini-3-Pro-Preview-Distill.bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7ac3d37cdeaad0176ccd0b340965e1c118c78f82e5cc399bfdb13c1ca09eaf
+size 29543424480

Qwen3-14B-Gemini-3-Pro-Preview-Distill.iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df02594508a577ea01e99317231b1a844f455fbac8dc4e317ebd9122771d7a92
+size 8597069280

Qwen3-14B-Gemini-3-Pro-Preview-Distill.q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a38fb51d9c2e052b13eab474c4524934b5390ae5201fa17d1aaad039a8fea85
+size 7321313760

Qwen3-14B-Gemini-3-Pro-Preview-Distill.q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:026c90bab5018375e520235716fa19563ea20e04425a17f0a534be00b6da8a4b
+size 6657106400

Qwen3-14B-Gemini-3-Pro-Preview-Distill.q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc76f75c6e83b5dcfe1eaffca087297d5a5150e990da56d949de9cdc08b216dd
+size 9001754080

Qwen3-14B-Gemini-3-Pro-Preview-Distill.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc96d145e88a1b4dd50dd01f7e6cc5a383b6e7d5233a93751de27aeffdfe5f03
+size 15698534880

README.md

@@ -0,0 +1,39 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+datasets:
+- TeichAI/gemini-3-pro-preview-high-reasoning-1000x
+base_model:
+- TeichAI/Qwen3-14B-Gemini-3-Pro-Preview-High-Reasoning-Distill
+---
+
+# Qwen3 14B Gemini 3 Pro Preview Reasoning Distill
+
+This model was trained on a **Gemini 3 Pro Preview** dataset with a high reasoning effort.
+
+- 🤖 Related Models:
+| Model      | Effective parameters      | Active parameters     |
+| ------------- | ------------- | ------------- |
+| [`TeichAI/Qwen3-8B-Gemini-3-Pro-Preview-Distill-GGUF`](https://huggingface.co/TeichAI/Qwen3-8B-Gemini-3-Pro-Preview-Distill-GGUF) | 8 B | 8 B |
+| [`TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-GGUF`](https://huggingface.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-GGUF) | 4 B | 4 B |
+
+
+- 🧬 Datasets:
+  - `TeichAI/gemini-3-pro-preview-high-reasoning-1000x`
+
+- 🏗 Base Model:
+  - `unsloth/Qwen3-14B`
+ 
+- ⚡ Use cases:
+  - Coding
+  - Science
+
+- ∑ Stats (Dataset)
+  - Costs: $ 32.7 (USD)
+  - Total tokens (input + output): 2.73 M
+
+---
+
+This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

config.json

@@ -0,0 +1,75 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "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",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_length": 8192,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 40,
+    "model_type": "qwen3",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.11.3",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

qwen3-14b.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cb62014d7afd9c327ddf51dffae77971523beaa1f4316a27eac00eb7563d7e
+size 29543424000

qwen3-14b.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84b5ad340f6fe357f4118b5e86444d82d7ced7fb27a7144793eff576ae3c74b
+size 15698534400