Add model-index eval YAML, arch spec, thinking docs, limitations, citation, ModelScope; remove column meanings note

README.md

@@ -1,77 +1,76 @@
 ---
-
 license: apache-2.0
-
 base_model: openbmb/MiniCPM5-1B
-
 tags:
-
 - gguf
-
 - llama.cpp
-
 - llama-cpp
-
 - ollama
-
 - lm-studio
-
 - minicpm
-
 - minicpm5
-
 - minicpm5-1b
-
 - tool-calling
-
 - function-calling
-
 - tool-use
-
 - agentic
-
 - agentic-ai
-
 - ai-agent
-
 - xml-tool-calling
-
 - json-function-calling
-
 - quantized
-
 - quantization
-
 - q4_k_m
-
 - q8_0
-
 - f16
-
 - gguf-my-repo
-
 - small-language-model
-
 - slm
-
 - edge-ai
-
 - on-device
-
 - local-llm
-
 - offline-ai
-
 - privacy
-
 - openbmb
-
 language:
-
 - en
-
 pipeline_tag: text-generation
-
+datasets:
+- Team-ACE/ToolACE
+model-index:
+- name: MiniCPM5-1B-Agentic-Tooluse-v3
+  results:
+  - task:
+      type: text-generation
+      name: Tool calling
+    dataset:
+      name: External ToolACE-derived first-call evaluation (held-out 300 examples)
+      type: Team-ACE/ToolACE
+    metrics:
+    - type: parseable_rate
+      value: 1.0000
+      name: Parseable tool-call rate
+    - type: valid_name_rate
+      value: 0.9867
+      name: Valid available-tool name rate
+    - type: expected_name_rate
+      value: 0.9533
+      name: Expected tool-name rate
+    - type: args_exact_rate
+      value: 0.7467
+      name: Exact-arguments rate
+    - type: arg_key_overlap
+      value: 0.9388
+      name: Argument-key overlap
+    - type: no_schema_copy_rate
+      value: 0.9967
+      name: No-schema-copy rate
+    - type: no_repetition_rate
+      value: 0.3400
+      name: No-repetition rate
+    - type: stopped_cleanly_rate
+      value: 0.0000
+      name: Stopped-cleanly rate
 ---
 
 # MiniCPM5-1B-Agentic-Tooluse-v3-GGUF — Local Function-Calling LLM (llama.cpp / Ollama / LM Studio)
@@ -112,15 +111,6 @@ negative result below is measured against it.
 | `arg_key_overlap` — F1 over argument keys | 0.8757 | 0.9422 | **0.9388** |
 | **mean of 5** | 0.8718 | 0.9245 | **0.9251** |
 
-Column meanings, to avoid the ambiguity the word "baseline" invites:
-**v2 (previous release)** = the previously published SFT adapter. An earlier draft of this card
-mislabeled this column "base model (untrained)" -- that was wrong; it is NOT the raw base model.
-The real untrained `openbmb/MiniCPM5-1B`, measured on this same test slice, scores `parseable`
-0.9333, `valid_name` 0.9133, `expected_name` 0.8867, `args_exact` 0.6300, `arg_key_overlap` 0.8920.
-**SFT retrain** = a fresh SFT pass from v2, prior to GRPO. **v3** = what this repo currently serves.
-Every "did it improve?" decision in this card is judged against **v2**, not against the untrained
-base model — beating an untrained model is not evidence of anything.
-
 GRPO buys +0.0100 on `args_exact`, the metric that matters here, and gives back 0.0034 (one test example
 each) on `expected_name` and `arg_key_overlap`. That trade is reported rather than hidden: the mean moves
 only +0.0006, so this is a targeted gain on the hardest metric, not a broad improvement.
@@ -216,6 +206,73 @@ ollama run minicpm5-tooluse-v3
 
 **How was this trained?** QLoRA supervised fine-tuning on tool-calling trajectories, followed by GRPO (Group Relative Policy Optimization) reinforcement-learning refinement targeting exact argument correctness.
 
+## Base model architecture
+
+MiniCPM5-1B uses a standard `LlamaForCausalLM` architecture:
+
+| Property | Value |
+|---|---|
+| Parameters (total) | 1,080,632,832 |
+| Parameters (non-embedding) | 679,552,512 |
+| Architecture | `LlamaForCausalLM` |
+| Layers | 24 |
+| Attention heads (GQA) | 16 Q / 2 KV |
+| Context length | 131,072 tokens |
+| Training | SFT → RL (GRPO) fine-tune on [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) |
+
+## Thinking mode
+
+MiniCPM5-1B has a built-in `<think>...</think>` chat template. The same checkpoint can act as a fast assistant **or** a deliberate chain-of-thought reasoner — controlled by a single flag:
+
+```python
+# Fast mode — recommended for tool calling (thinking OFF)
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True,
+    enable_thinking=False,
+    tokenize=False,
+)
+
+# Reasoning mode (thinking ON — NOT recommended for tool calling)
+prompt = tokenizer.apply_chat_template(
+    messages, tools=tools, add_generation_prompt=True,
+    enable_thinking=True,
+    tokenize=False,
+)
+```
+
+> **Important:** always use `enable_thinking=False` for tool/function calling. With thinking ON the model spends its token budget inside `<think>...</think>` and may not reach a completed function call. All benchmark numbers in this card use thinking OFF.
+
+## Citation
+
+If you use this model, please cite the base model paper:
+
+```bibtex
+@article{minicpm4,
+  title   = {MiniCPM4: Ultra-Efficient LLMs on End Devices},
+  author  = {MiniCPM Team},
+  journal = {arXiv preprint arXiv:2506.07900},
+  year    = {2025}
+}
+```
+
+And the ToolACE dataset used for fine-tuning:
+
+```bibtex
+@article{toolace,
+  title   = {ToolACE: Winning the Points of LLM Function Calling},
+  author  = {Liu, Ying and others},
+  journal = {arXiv preprint arXiv:2409.00920},
+  year    = {2024}
+}
+```
+
+## ModelScope
+
+The base model is also available on ModelScope (for users in China and East Asia):
+
+- [OpenBMB/MiniCPM5-1B on ModelScope](https://www.modelscope.cn/models/OpenBMB/MiniCPM5-1B)
+
+*(The fine-tuned adapter/GGUF builds are currently HuggingFace-only.)*
 ## Related repos
 
 ### v3 model family (this release)
@@ -237,3 +294,4 @@ ollama run minicpm5-tooluse-v3
 
 Built on [MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) by OpenBMB, fine-tuned for agentic tool/function calling and refined with GRPO reinforcement learning.
 
+## Limitations