初始化项目，由ModelHub XC社区提供模型

Model: TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF Source: Original Platform
2026-06-04 03:22:15 +08:00
commit 4bd8a0974a
17 changed files with 242 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,48 @@
+*.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
+qwen3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-8b.F16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/59
+++ b/59
@@ -0,0 +1,59 @@
+
+FROM qwen3-8b.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
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.bf16.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.bf16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781d1ed03110f38c127a65b8273b639108494081fc55ff3ec3a52643a3c7e923
+size 16388044704
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_m.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff197aefbab7a8b9e01f7f0932a42c71ec01780f9b88850cd8521e81c18697db
+size 3051914784
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_xs.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq2_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dc793af6dbbf419540ea7dc21a0b354ef5b922111a096fae78e5ad264397f4f
+size 2696156704
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_m.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0cc092414e336e55126e824ff575ec031481a3bbcaf3d00effa4ba85d799cc1
+size 3896620576
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_xs.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq3_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f8381ea036178e38ce8e7958c49d13aa46902c9ca5fcd1ea44d1ceb947107c
+size 3626874400
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_nl.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_nl.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c63d9331e4630cafd67da2bc38bc1e127f34455d60ae3e557c0534f6bc9acd
+size 4818790304
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_xs.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.iq4_xs.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81307764182f84db095ea0788be3062552202d617ee2474aedb060279a9aa812
+size 4561839648
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_m.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63336bdd74a145e5c19755416debf628695b9743c38901c2f56e6230cfea5554
+size 4124161952
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_s.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q3_k_s.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6829e098cd23b7c0158a5bbe6d1e424544c6a9ed05697ec9f348f5f6d0d9152b
+size 3769612192
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q4_k_m.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q4_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c75ece2600926750c40ee7f0cd29a73488170588b4baaa8758518470e0ed43
+size 5027784608
--- a/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q8_0.gguf
+++ b/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill.q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5fa0eed586696564e4b3820dc3e47a77ab526fcaf454690e036f96bb304fe4
+size 8709519264
--- a/README.md
+++ b/README.md
@@ -0,0 +1,25 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+datasets:
+- TeichAI/deepseek-v3.2-speciale-1000x
+base_model:
+- TeichAI/Qwen3-8B-DeepSeek-v3.2-Speciale-Distill
+---
+
+# Qwen3-8B-DeepSeek-v3.2-Speciale-Distill-GGUF - GGUF
+
+This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+
+**Example usage**:
+- For text only LLMs:    **llama-cli** **--hf** repo_id/model_name **-p** "why is the sky blue?"
+- For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
+
+## Available Model files:
+- `qwen3-8b.Q8_0.gguf`
+- `qwen3-8b.F16.gguf`
+
+## Ollama
+An Ollama Modelfile is included for easy deployment.
--- a/config.json
+++ b/config.json
@@ -0,0 +1,71 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "torch_dtype": "bfloat16",
+    "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_length": 2048,
+    "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": 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
+}
--- a/qwen3-8b.F16.gguf
+++ b/qwen3-8b.F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f02608f3f8f25769945b74e1520dfff82f2f1ba6243f62d6b805d3ebe2ffe5
+size 16388044224
--- a/qwen3-8b.Q8_0.gguf
+++ b/qwen3-8b.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73631d1d4bd219f8db5f25e8ce6dfb9bd1d27022a3f1eb26c8cc1562ec1c479
+size 8709518784