初始化项目，由ModelHub XC社区提供模型

Model: delimitter/synoema-coder-1.5b-tools-v12 Source: Original Platform
2026-06-29 20:45:36 +08:00
commit 69799ab629
11 changed files with 323 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,39 @@
+*.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
+synoema-coder-1.5b-tools-v12.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+synoema-coder-1.5b-tools-v12.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+synoema-coder-1.5b-tools-v12.f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,139 @@
+---
+language: [en]
+license: apache-2.0
+base_model: unsloth/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags: [synoema, tool-use, agentic, function-calling, lora, qlora, code, qwen2.5, gguf]
+model-index:
+- name: synoema-coder-1.5b-tools-v12
+  results:
+  - task: {type: tool-use, name: Synoema MCP Agentic Tool-Use Eval (28 tasks)}
+    metrics:
+    - {type: pass@1, value: 1.0, name: "28-task agentic eval (28/28)"}
+---
+
+# Synoema-Coder-1.5B Tools (C12)
+
+A **1.5B** LoRA fine-tune of `unsloth/Qwen2.5-1.5B-Instruct` that turns it into an **agentic coding model for the
+[Synoema](https://synoema.tech) programming language** — it writes Synoema, type-checks it,
+runs it, searches a corpus, and self-corrects on errors, all through MCP tools.
+
+- 🌐 **Website:** https://synoema.tech
+- 🤖 **This model:** https://huggingface.co/delimitter/synoema-coder-1.5b-tools-v12
+- 📚 **Training corpus (dataset):** https://huggingface.co/datasets/delimitter/synoema-coder-3b-tools-corpus
+
+---
+
+## 🏆 Result: **100% (28/28)** on the Synoema agentic tool-use benchmark
+
+Scored on the **corrected agentic harness**: the model is driven **turn-by-turn** (generation
+stops at `<|im_end|>`), and **real** tool results are injected between turns — actual
+`sno check` / `sno run` output from the live Synoema compiler, never mocked. A task only passes
+if the model genuinely completes it end-to-end (e.g. multi-write self-correction: write broken
+code → observe the type error → rewrite a valid fix → type-check passes).
+
+| Capability | Tasks | Pass |
+|---|---|---|
+| Write + typecheck + run | TU1–TU3, TU5, TU10 | ✅ |
+| Search → write → run | TU6, TU9, TU20 | ✅ |
+| Multi-write self-correction (if/else → ternary) | TU4, TU13 | ✅ |
+| Language features (ADT, HOF, pattern match, cons) | TU11, TU14–TU19, TU23, TU29 | ✅ |
+| List comprehensions | TU12, TU26 | ✅ |
+| Nested ternary (fizzbuzz) | TU22, TU30 | ✅ |
+| **Total** | **28** | **28/28** |
+
+---
+
+## What is Synoema?
+
+[Synoema](https://synoema.tech) is an **LLM-native programming language and runtime** designed so
+that models can write it reliably:
+
+- **BPE-aligned operators** — every operator maps to exactly one `cl100k_base` token.
+- **Ternary instead of if/else** — `? cond -> a : b` (nestable).
+- **GBNF grammar** for constrained decoding (structural-correctness guarantee).
+- **Cranelift JIT + WebAssembly** compile targets.
+- **MCP server** exposing `file_write`, `file_read`, `sno_typecheck`, `sno_run`, `search_corpus`.
+- **Contract annotations** (`requires` / `ensures`) for formal verification.
+
+---
+
+## Model details
+
+| Property | Value |
+|---|---|
+| Base model | `unsloth/Qwen2.5-1.5B-Instruct` |
+| Parameters | 1.5B |
+| Method | QLoRA (4-bit NF4 + LoRA), merged to fp16 for GGUF |
+| LoRA | r=16, alpha=32 |
+| Sequence length | 1024 |
+| Epochs / cycle | 3 |
+| Training corpus | ~18k tool-use + codegen examples — **every example passes `sno check` + `sno run`** |
+| Cycle | C12 (sequential "carousel": each cycle warm-starts from the best previous adapter, then trains on the corpus plus targeted examples for the prior cycle's failures) |
+| Hardware | AMD RX 7900 GRE 16GB (ROCm + unsloth) |
+
+---
+
+## GGUF files (llama.cpp / Ollama / LM Studio)
+
+| File | Quant | Size | Notes |
+|---|---|---|---|
+| `synoema-coder-1.5b-tools-v12.Q4_K_M.gguf` | Q4_K_M | 940 MB | smallest, recommended for local use |
+| `synoema-coder-1.5b-tools-v12.Q8_0.gguf` | Q8_0 | 2 GB | near-lossless |
+| `synoema-coder-1.5b-tools-v12.f16.gguf` | F16 | 3 GB | full precision |
+
+```bash
+# llama.cpp
+llama-cli -hf delimitter/synoema-coder-1.5b-tools-v12 --hf-file synoema-coder-1.5b-tools-v12.Q4_K_M.gguf -p "Write quicksort in Synoema to src/qs.sno and run it."
+
+# Ollama
+ollama run hf.co/delimitter/synoema-coder-1.5b-tools-v12:Q4_K_M
+```
+
+---
+
+## Usage — Transformers + PEFT (adapter)
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-1.5B-Instruct", device_map="auto")
+tok  = AutoTokenizer.from_pretrained("unsloth/Qwen2.5-1.5B-Instruct")
+model = PeftModel.from_pretrained(base, "delimitter/synoema-coder-1.5b-tools-v12")
+```
+
+Prompt format is **ChatML**. The system prompt used at training/eval:
+
+```
+<|im_start|>system
+You are sno-code, a Synoema coding agent. Use tools to write and verify code.<|im_end|>
+<|im_start|>user
+Write `square x = x * x` with `main = square 9` to src/square.sno, typecheck and run it.<|im_end|>
+<|im_start|>assistant
+```
+
+The model emits OpenAI-style `tool_calls` for `file_write`, `sno_typecheck`, `sno_run`,
+`file_read`, `search_corpus`; feed real tool results back as `tool` turns.
+
+---
+
+## Synoema language quick reference
+
+```synoema
+maxOf x y = ? x > y -> x : y            -- ternary (NO if/then/else)
+fact 0 = 1                              -- pattern matching
+fact n = n * fact (n - 1)
+evens xs = [x | x <- xs, x % 2 == 0]    -- list comprehension
+sumList xs = foldl (\acc x -> acc + x) 0 xs   -- higher-order functions
+Direction = North | South | East | West       -- ADT
+opposite North = South
+main = qsort [3 1 4 1 5]                -- lists are SPACE-separated
+```
+
+---
+
+## License
+
+Apache-2.0 (same as the Qwen2.5 base model). **Synoema** © Andrey Bubnov — https://synoema.tech
--- a/adapter_config.json
+++ b/adapter_config.json
@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/adapter_model.safetensors
+++ b/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a2bb8ca66fb1dfaed6ff2dda670d31f99c286af3682ceb14a6d11bfe02e6f9
+size 73911112
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}
--- a/synoema-coder-1.5b-tools-v12.Q4_K_M.gguf
+++ b/synoema-coder-1.5b-tools-v12.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669e3378cacfc7760310a62907fce51354e3f46721b1ddf55da04443029d6b8d
+size 986048032
--- a/synoema-coder-1.5b-tools-v12.Q8_0.gguf
+++ b/synoema-coder-1.5b-tools-v12.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a46431d5d97e74106b5f970347d34de7612867ff23fe179705bceaf5ab16af
+size 1646572576
--- a/synoema-coder-1.5b-tools-v12.f16.gguf
+++ b/synoema-coder-1.5b-tools-v12.f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4526812f21a0afbb20945f9fc699c24d3e23a9444baa552b38c9a4cdbffdec
+size 3093668896
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
+size 11422356
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/training_summary.json
+++ b/training_summary.json
@@ -0,0 +1,11 @@
+{
+  "model": "/home/abubnov/synoema/research/finetune/mcp/output/seq-qwen2.5-1.5b-tools-c11",
+  "train_mode": "causal_lm_qlora",
+  "examples": 17087,
+  "codegen": 6000,
+  "interrogator": 0,
+  "epochs": 3,
+  "lora_r": 16,
+  "train_seconds": 17522,
+  "output": "/home/abubnov/synoema/research/finetune/mcp/output/seq-qwen2.5-1.5b-tools-c12"
+}