初始化项目，由ModelHub XC社区提供模型

Model: anan139/NoNonsense-Historian-7B-GGUF Source: Original Platform
2026-06-04 12:54:16 +08:00
commit ee876d1be5
6 changed files with 131 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,38 @@
+*.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-7B.F16.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
--- a/DeepSeek-R1-Distill-Qwen-7B.F16.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B.F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60001307003665529156ed43ddbc041d88c03a1c14a1518192c6a17fbb60f671
+size 15237853024
--- a/DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399b0230ab24d372c0298baca001d99a1e3b33f88ccd806dc0533bfd1fdb8a01
+size 4683073376
--- a/DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf
+++ b/DeepSeek-R1-Distill-Qwen-7B.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48f73b49be6837155fd95a56690f79a41c3a3b1f401e93af67746b61e0dcf8d
+size 8098525024
--- a/README.md
+++ b/README.md
@@ -0,0 +1,23 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+
+---
+
+# NoNonsense-Historian-7B-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.cpp/llama-cli -hf anan139/NoNonsense-Historian-7B-GGUF --jinja`
+- For multimodal models: `./llama.cpp/llama-mtmd-cli -hf anan139/NoNonsense-Historian-7B-GGUF --jinja`
+
+## Available Model files:
+- `DeepSeek-R1-Distill-Qwen-7B.Q4_K_M.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)
--- a/config.json
+++ b/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": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "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": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "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": "2026.2.1",
+    "use_cache": true,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}