初始化项目，由ModelHub XC社区提供模型

Model: hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v9
Source: Original Platform

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final-model.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-f16.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v9-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

MiniCPM5-1B-Agentic-v9-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31926ef26f7d5b9d1f7b2fab8397290402ba3f757e30c11c68c7901cac00438d
+size 2166551872

MiniCPM5-1B-Agentic-v9-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:946b9ac9e65f7c735c352015ad0bbc0ec9170b1c3fdb2a66a7ed9ae5190cc6f6
+size 485829952

MiniCPM5-1B-Agentic-v9-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6415747ff270f691c689664af0624aabe56bc04c88b60a3029b39e4ade68f2c7
+size 582899008

MiniCPM5-1B-Agentic-v9-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d6ab985bccfa01e2aac38a9632e88e638ce08411f843fe9f668e72a29d5cce
+size 688065856

MiniCPM5-1B-Agentic-v9-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafdc25d646b4015403bdab3199ca4771dd0d900edcc5660671a4b5a1acb632d
+size 786861376

MiniCPM5-1B-Agentic-v9-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443c701fb5a835baf67d54782923c69e5e0701fd030585e2ebec0dbb4c2f8290
+size 1153529152

README.md

@@ -0,0 +1,52 @@
+---
+license: other
+language:
+- en
+base_model:
+- openbmb/MiniCPM5-1B
+tags:
+- agentic
+- coding
+- agent
+- gguf
+---
+
+# MiniCPM5-1B-Agentic-v9
+
+Created by GLM-5.2. Model 9 in the agentic post-training series.
+
+**Training**: SFT on 10 hand-crafted agentic trajectories (8 epochs, lr=5e-6) teaching the model to use bash tools concisely without excessive reasoning loops.
+
+## Evaluation
+
+| Metric | Score |
+|---|---|
+| Agentic Eval (20 tasks) | 30.0% (6/20) |
+| Real-World Tasks (12 tasks) | 0% (0/12) |
+
+Tasks passed: create_file, fibonacci, fix_bug2, grep_search, csv_analyze, merge_files
+
+GGUFs available: f16, q8_0, q5_k_m, q4_k_m, q3_k_m, q2_k
+
+## Quantization Recommendations
+
+This is a 1B model — heavier quantization degrades output quality significantly.
+
+| Quant | Quality | Size | Recommendation |
+|---|---|---|---|
+| f16 | Full | ~2.1GB | Best quality |
+| q8_0 | Excellent | ~1.1GB | **Recommended** — near-identical to f16 |
+| q5_k_m | Good | ~0.8GB | Reasoning OK, response may degrade on longer outputs |
+| q4_k_m | Fair | ~0.7GB | Reasoning OK, response degrades into repetition |
+| q3_k_m | Poor | ~0.6GB | Not recommended |
+| q2_k | Poor | ~0.5GB | Not recommended |
+
+**For production use, prefer q8_0 or f16.** The model uses reasoning tokens; lower quantizations break the transition from reasoning to response.
+
+## Chat Template
+
+The GGUF chat template defaults to `enable_thinking=true`, so the model will always produce reasoning followed by response. If your inference engine supports `enable_thinking=false`, you can skip reasoning for faster responses.
+
+## Tool Use
+
+The model supports bash tool calls using the `<function name="bash">` XML format. The chat template includes tool definitions when tools are provided.

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/workspace/URM-LLM/models/MiniCPM5-1B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4608,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 130560
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "temperature": 0.9,
+  "top_p": 0.95,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f4cc7a362f400311801ecf6182dedc88e37d72109e16e4d52fe269bbcf8864
+size 2161290912

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9a7a7681ea0f9eb3bedda5b1a5f1f54347f9f29ff27d32d8d09e9d0b0b6472
+size 12484859