初始化项目，由ModelHub XC社区提供模型

Model: hudsongouge/minicpm5-1B-GLM-5.2-Agentic-v8
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
+MiniCPM5-1B-Agentic-v8-f16.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v8-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v8-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v8-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v8-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+MiniCPM5-1B-Agentic-v8-q2_k.gguf filter=lfs diff=lfs merge=lfs -text

MiniCPM5-1B-Agentic-v8-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62398f6a061735c2d6139f114b150b721a314af60cf086c3307d076a3dce6080
+size 2166552160

MiniCPM5-1B-Agentic-v8-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe8b463fda16e94a6e20ce7fca8f1196c71f326608205ff40240917d5939dbb
+size 485830240

MiniCPM5-1B-Agentic-v8-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92945971c46cb415eba72b3c77d69b6c06a8880689e4188ade40611f7efaa1f
+size 582899296

MiniCPM5-1B-Agentic-v8-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0e6b3031bea013708bea17aa403c66300264f2f7b2b4a7b7492371ff0cd94b
+size 688066144

MiniCPM5-1B-Agentic-v8-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5b800043f134334fcb502c24a3042f8bd735856fec0d21020589f3dcc8a3ca
+size 786861664

MiniCPM5-1B-Agentic-v8-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b1a5f3ad217da12a04ad7830bfdd5f0635a11d70d1cc244e33bad3eb939c87
+size 1153529440

README.md

@@ -0,0 +1,48 @@
+---
+license: other
+language:
+- en
+base_model:
+- openbmb/MiniCPM5-1B
+tags:
+- agentic
+- coding
+- agent
+- gguf
+---
+
+# MiniCPM5-1B-Agentic-v8
+
+Created by GLM-5.2. Model 8 of 8 in the agentic post-training series.
+
+**Variant**: 4-way Soup (best overall)
+
+## Evaluation
+
+| Metric | Score |
+|---|---|
+| Real-World Tasks | 33.3% (4/12) |
+| Unique Tasks Solved | 8/12 |
+| Consistent (5/5) | rw_http_server |
+| Often (4/5) | rw_venv_setup |
+
+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.

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/checkpoints/rft-v1/final",
+  "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": false,
+  "vocab_size": 130560
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    1,
+    130073
+  ],
+  "pad_token_id": 1,
+  "transformers_version": "4.49.0",
+  "do_sample": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b11c4c9b866dda4759355fd96c1a1499ac2703b444c75661967ccc45b0644f3
+size 2161290944

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
+  }
+}