初始化项目，由ModelHub XC社区提供模型

Model: koshuro/Qwen-DeepSeek-1.5B-Agentic-distill
Source: Original Platform

.gitattributes

@@ -0,0 +1,41 @@
+*.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
+deepseek-r1-distill-qwen-1.5b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-qwen-1.5b.F16.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-qwen-1.5b.Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-qwen-1.5b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-qwen-1.5b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-qwen-1.5b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+datasets:
+- DJLougen/hermes-agent-traces-filtered
+language:
+- en
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
+pipeline_tag: text-generation
+---
+
+# Qwen-DeepSeek-1.5B-Agentic-distill : GGUF
+
+This model was finetuned on 1 billion tokens of filtered reasoning traces, mainly consisting off tool use, agentic work, and repository work.
+
+
+---
+## Benchmark results VS a similar sized model.
+![compare_bar_objective](https://cdn-uploads.huggingface.co/production/uploads/683150652abe09530517e8ed/tZRIF11m0FaUnVt3qluxx.png)
+
+
+
+
+
+
+
+
+
+
+
+**Example usage**:
+- For text only LLMs:    `llama-cli -hf koshuro/Qwen-DeepSeek-1.5B-Agentic-distill --jinja`
+- For multimodal models: `llama-mtmd-cli -hf koshuro/Qwen-DeepSeek-1.5B-Agentic-distill --jinja`
+
+## Available Model files:
+- `deepseek-r1-distill-qwen-1.5b.Q3_K_M.gguf`
+- `deepseek-r1-distill-qwen-1.5b.F16.gguf`
+- `deepseek-r1-distill-qwen-1.5b.Q2_K_L.gguf`
+- `deepseek-r1-distill-qwen-1.5b.Q4_K_M.gguf`
+- `deepseek-r1-distill-qwen-1.5b.Q6_K.gguf`
+- `deepseek-r1-distill-qwen-1.5b.Q8_0.gguf`
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+## Note
+The model's BOS token behavior was adjusted for GGUF compatibility.
+This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

config.json

@@ -0,0 +1,61 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151646,
+    "torch_dtype": "float16",
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "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"
+    ],
+    "max_position_embeddings": 131072,
+    "max_window_layers": 21,
+    "model_type": "qwen2",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "pad_token_id": 151654,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.7.6",
+    "use_cache": false,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

deepseek-r1-distill-qwen-1.5b.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af48f5bff6a4389bfa9de4b0d0e894c781b0916954daf4b54b61a1ab1545cde
+size 3560416288

deepseek-r1-distill-qwen-1.5b.Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c4dfa7a437b328f66fc8ea8bf5a8b206c5fbf59e5bd930b930fca2c6cf64b7
+size 980784160

deepseek-r1-distill-qwen-1.5b.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997e9acef639a4b5708032b329c0ec3ec95e9c487cb3b7f936bbec696df757c9
+size 924455968

deepseek-r1-distill-qwen-1.5b.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00fd6a1c4e21c5c04eddb4c1967bd7f89399ca1b3bce191e81b787e619a3246
+size 1117320736

deepseek-r1-distill-qwen-1.5b.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c601275e4cc9556f68af73ec4e55048d63308721a152400c2a5576cf8bcc69f7
+size 1464178720

deepseek-r1-distill-qwen-1.5b.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f537de14c2e78f492e78c5819da9687b852f6d58973144d368fbd8e8dd1ecf
+size 1894532128