初始化项目，由ModelHub XC社区提供模型

Model: seanpoyner/smolcode-coder-1.5b-tools Source: Original Platform
2026-07-18 13:18:10 +08:00
commit 013b3644cd
10 changed files with 360 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,37 @@
+*.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
+smolcode-1.5b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/73
+++ b/73
@@ -0,0 +1,73 @@
+# Ollama Modelfile for the smolcode fine-tuned 1.5B tool-caller.
+#
+# Build (on HAL, after pulling the merged model out of the Modal volume):
+#   modal volume get smolcode-ft out/merged ./smolcode-merged
+#   ollama create smolcode-coder-1.5b:tools -f finetune/Modelfile
+#
+# The tag `smolcode-coder-1.5b:tools` matches the `hal-smol` preset's tier 0
+# (engine/config.py). Ollama imports the safetensors dir directly (no manual GGUF
+# step). The TEMPLATE is Qwen2.5's tool-calling chat format — the SAME format the
+# model was trained/eval'd on (finetune/qwen_template.py) — so served prompts match.
+
+FROM ./smolcode-1.5b-q4_k_m.gguf
+
+# Qwen2.5 tool-calling template (renders <tools> in the system turn and parses
+# <tool_call> from the assistant). Verify with the curl test in serve_and_bench.md.
+TEMPLATE """{{- if .Messages }}
+{{- if or .System .Tools }}<|im_start|>system
+{{- if .System }}
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{{- range .Tools }}
+{"type": "function", "function": {{ .Function }}}
+{{- end }}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+{{- end }}<|im_end|>
+{{ end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if eq .Role "user" }}<|im_start|>user
+{{ .Content }}<|im_end|>
+{{ else if eq .Role "assistant" }}<|im_start|>assistant
+{{ if .Content }}{{ .Content }}
+{{- else if .ToolCalls }}<tool_call>
+{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
+{{ end }}</tool_call>
+{{- end }}{{ if not $last }}<|im_end|>
+{{ end }}
+{{- else if eq .Role "tool" }}<|im_start|>user
+<tool_response>
+{{ .Content }}
+</tool_response><|im_end|>
+{{ end }}
+{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
+{{ end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
+
+PARAMETER temperature 0
+# CRITICAL: repeat_penalty must be 1.0. The tool system prompt literally contains
+# the <tool_call> token, so Ollama's default 1.1 penalty suppresses the model from
+# emitting it — the exact bug that made eval show 0% native tool calls.
+PARAMETER repeat_penalty 1.0
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<|im_start|>"
--- a/README.md
+++ b/README.md
@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+tags:
+- code
+- function-calling
+- tool-use
+- agent
+- small-language-model
+datasets:
+- NousResearch/hermes-function-calling-v1
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# smolcode-coder-1.5b-tools
+
+A LoRA fine-tune of **Qwen2.5-Coder-1.5B-Instruct** that teaches the model to emit
+**native `<tool_call>` function calls**, so a 1.5B *coder* model can actually drive an
+agentic write → run → fix → verify loop.
+
+Built for [**smolcode**](https://gitea.poyner.ai/sean/smolcode) — an SLM-optimized
+agentic coding assistant — for the Hugging Face **Build Small** hackathon.
+
+## Demo
+
+[▶️ Watch this model drive the agent](https://huggingface.co/spaces/seanpoyner/smolcode/resolve/main/demo.mp4) — in the smolcode Space, the **Auto** router resolves to this fine-tuned 1.5B ("routed to custom") and runs the write → run → fix → verify loop in the smol-dark UI. Try it live: [huggingface.co/spaces/seanpoyner/smolcode](https://huggingface.co/spaces/seanpoyner/smolcode).
+
+## Why
+Out of the box, small Qwen-Coder models describe tool calls as plain-text/```json
+instead of emitting the native `<tool_call>` token (id 151657) that runtimes (Ollama,
+llama.cpp) parse into OpenAI-style `tool_calls` — which breaks agentic loops. This
+fine-tune closes that gap on a tiny (1.5B) model: **100% native `<tool_call>` emission**
+in free generation on held-out prompts (base model: 0%).
+
+## Results
+- **Native tool-call rate:** 100% (16/16 held-out prompts) — the release gate.
+- **Agentic bench (smolcode pass@1, 10 tasks):** 9/10 as the entry tier of a
+  1.5B→8B→30B ladder, solving **7/10 entirely on its own** (2–16s each). For
+  comparison the all-Granite ladder (3B entry) scores 10/10 — the 1.5B carries the
+  same standalone load as a 2×-larger 3B.
+- **Train loss:** 0.138 (3 epochs, assistant-only loss).
+
+## Training
+- **Base:** Qwen/Qwen2.5-Coder-1.5B-Instruct
+- **Method:** bf16 LoRA (r=16, α=32) on attention + MLP projections, **plus full
+  training of `embed_tokens` + `lm_head`** (`modules_to_save`) — required so the model
+  can *output* the `<tool_call>` special token, which LoRA on attention/MLP alone
+  cannot. **Assistant-only loss** (loss on tool calls + final answers only).
+- **Data:** NousResearch/hermes-function-calling-v1 (breadth) + synthetic smolcode
+  tool-use trajectories (sharpness), all rendered through the *same*
+  `apply_chat_template(tools=...)` used at inference — training target is byte-identical
+  to the served prompt (fixes the v1 train/inference template mismatch).
+- **Schedule:** 3 epochs, full 2048 sequence length. Trained on Modal (A100).
+
+## Serving — read this, two non-obvious requirements
+1. **Serve via the GGUF, not the safetensors directly.** Ollama's bf16-safetensors
+   auto-import produces garbage (`??????`) for this model. Use the included
+   `smolcode-1.5b-q4_k_m.gguf` (converted with llama.cpp `convert_hf_to_gguf.py`):
+   ```bash
+   ollama create smolcode-coder-1.5b:tools -f Modelfile   # Modelfile is in this repo
+   ```
+2. **`repeat_penalty` / `repetition_penalty` MUST be 1.0.** The tool system prompt
+   literally contains the `<tool_call>` token, so any penalty > 1 suppresses the model
+   from emitting it (you'll see a stray token + bare JSON instead). The included
+   `Modelfile` sets `PARAMETER repeat_penalty 1.0`. For raw `transformers.generate`,
+   pass `repetition_penalty=1.0`.
+
+With those, Ollama's `/v1/chat/completions` returns proper native `tool_calls`.
+
+## Use (transformers)
+Standard Qwen2.5 chat template with `tools=`; greedy, `repetition_penalty=1.0`. The
+model responds with `<tool_call>{"name": ..., "arguments": ...}</tool_call>`.
+
+## Files
+- `model.safetensors` + tokenizer/config — the merged model (lm_head untied).
+- `smolcode-1.5b-q4_k_m.gguf` — quantized GGUF for serving.
+- `Modelfile` — Ollama import recipe (template + `repeat_penalty 1.0`).
+
+## License
+Apache-2.0 (inherits from the base model).
--- 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/config.json
+++ b/config.json
@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "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": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.12.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743374660b8c833b425d3599e8c8734c2af8272fdde5c6ef005bfd43d52827b1
+size 3554214752
--- a/smolcode-1.5b-q4_k_m.gguf
+++ b/smolcode-1.5b-q4_k_m.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254b44fc3c5d6ec9c42c677f5c43df654dd4b5af3eb3adb3c7a89ab11ec94e9c
+size 1117321568
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}