初始化项目，由ModelHub XC社区提供模型

Model: Nanthasit/sakthai-context-0.5b-tools Source: Original Platform
2026-08-22 10:15:18 +08:00
commit f43581c75c
17 changed files with 1251 additions and 0 deletions
--- a/.eval_results/benchmark-20260731_015807.yaml
+++ b/.eval_results/benchmark-20260731_015807.yaml
@@ -0,0 +1,22 @@
+model: Nanthasit/sakthai-context-0.5b-tools
+benchmark_ts: '2026-07-31T01:58:07Z'
+backend: transformers-cpu
+prompt_type: tool_calling_weather
+prompt_length_chars: 691
+prompt: "<tools>\n[\n  {\n    \"name\": \"get_weather\",\n    \"description\": \"\
+  Get current weather for a city\",\n    \"p..."
+total_time_s: 16.81
+load_time_s: 10.38
+gen_time_s: 2.54
+input_tokens: 181
+output_tokens: 21
+has_tool_call: true
+has_correct_answer: true
+has_valid_json: false
+response: '
+
+  [{"name": "get_weather", "arguments": {"location": "Tokyo"}}
+
+  ]'
+device: cpu
+dtype: torch.bfloat16
--- a/.eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260731T231603Z.yaml
+++ b/.eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260731T231603Z.yaml
@@ -0,0 +1,39 @@
+# Cron Eval Result: Nanthasit/sakthai-context-0.5b-tools
+# Generated: 2026-07-31T23:16:03.251125+00:00
+# Mode: metadata-only cron
+# Tracker: hf-eval-updated.json
+
+model_id: Nanthasit/sakthai-context-0.5b-tools
+eval_date: "2026-07-31T23:16:03.251125+00:00"
+eval_type: metadata_cron
+
+metadata:
+  pipeline_tag: text-generation
+  library_name: transformers
+  license: apache-2.0
+  gated: false
+  private: false
+  created_at: "2026-07-04T22:27:20.000Z"
+  last_modified: "2026-07-31T23:16:03.251125+00:00"
+  age_days: 27.03
+  sha: "06cf87a05659b446fa0a8c98e1f5aa0f21c0e4e9"
+  tags: ["transformers", "safetensors", "qwen2", "text-generation", "agent", "conversational", "ollama", "small-language-model", "slm", "tool-use", "qwen", "qwen2.5", "sakthai", "house-of-sak", "tool-calling", "function-calling", "merged", "edge", "lightweight", "low-resource", "raspberry-pi", "on-device", "benchmark", "eval", "en", "dataset:Nanthasit/sakthai-combined-v7", "dataset:Nanthasit/sakthai-bench-v2", "arxiv:2412.15115", "base_model:Qwen/Qwen2.5-0.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct", "license:apache-2.0", "model-index", "eval-results", "text-generation-inference", "endpoints_compatible", "region:us"]
+
+metrics:
+  downloads: 251
+  likes: 0
+  trending_score: None
+  download_velocity:
+    downloads_per_day: 9.28
+    age_days: 27.03
+    assessment: >-
+      Steady interest for a 0.5B edge tool-use model; ~9.3 downloads/day.
+  note: >-
+    No live inference benchmark in this run; result is metadata-driven health snapshot.
+    Tool-calling trajectory inferred from tags and dataset lineage (sakthai-combined-v7, sakthai-bench-v2).
+
+highlights:
+  - "Base model: Qwen/Qwen2.5-0.5B-Instruct"
+  - "Use case: lightweight tool-use / function-calling / on-device"
+  - "Eval results folder updated: 2026-07-31T23:16:03.251125+00:00"
+  - "Tracker run metadata_cron"
--- a/.eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260801T032221Z.yaml
+++ b/.eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260801T032221Z.yaml
@@ -0,0 +1,36 @@
+model: Nanthasit/sakthai-context-0.5b-tools
+timestamp: '2026-08-01T03:22:21.947742+00:00'
+source: metadata-snapshot
+repo:
+  last_modified: '2026-08-01T00:30:00+00:00'
+  downloads: 251
+  likes: 0
+  private: false
+  gated: false
+  sha: 285d218adbae87fac023d32a800562f578ed9d76
+metrics:
+- name: Selection Accuracy
+  value: 91.2
+  verified: false
+- name: Arguments Accuracy
+  value: 45.7
+  verified: false
+- name: Strict Accuracy
+  value: 45.7
+  verified: false
+- name: Held-Out Tool Accuracy
+  value: 87.8
+  verified: false
+- name: Degenerate Outputs
+  value: 0
+  verified: false
+inference:
+  temperature: 0.01
+  max_new_tokens: 256
+  top_p: 0.9
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+datasets:
+- Nanthasit/sakthai-combined-v7
+- Nanthasit/sakthai-bench-v2
+pipeline_tag: text-generation
+notes: Metadata-based eval snapshot from cron.
--- a/.eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-1.yaml
+++ b/.eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-1.yaml
@@ -0,0 +1,227 @@
+target_model:
+  id: Nanthasit/sakthai-context-0.5b-tools
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  downloads: 94
+  likes: 0
+  private: false
+  gated: false
+  created: 2026-07-04T22:27:20.000Z
+  last_modified: 2026-07-31T04:47:54.000Z
+  model_age_days: 26.28
+  model_type: merged full SFT (494M params, bfloat16, ~942 MB safetensors)
+  has_weights: true
+
+architecture:
+  model_type: qwen2
+  architectures: ["Qwen2ForCausalLM"]
+  hidden_size: 896
+  num_hidden_layers: 24
+  num_attention_heads: 14
+  num_key_value_heads: 2
+  intermediate_size: 4864
+  vocab_size: 151936
+  max_position_embeddings: 32768
+  total_parameters: 494032768
+  dtype: bfloat16
+  rope_theta: 1000000
+  rope_type: default
+  tie_word_embeddings: true
+  attention: full (24/24 full_attention layers; sliding_window null — no SWA)
+  transformers_version: 5.14.1
+
+repo_summary:
+  siblings_count: 9
+  total_repo_bytes: 999542790
+  total_gb: 0.931
+  has_weights: true
+  weight_file_count: 1
+  weight_files: ["model.safetensors (988,097,824 bytes, ~942 MB BF16)"]
+  config_present: true
+  tokenizer_present: true
+  chat_template_present: true
+  readme_present: true
+  readme_size_bytes: 16229
+  eval_files_present: 1
+  eval_files: [".eval_results/benchmark-20260731_015807.yaml"]
+  note: >-
+    Clean 9-file merged repo — single BF16 safetensors, full tokenizer +
+    chat_template.jinja, no junk. GGUF lives in the merged sibling
+    (sakthai-context-0.5b-merged), which this README links for CPU users.
+
+benchmarks:
+  model_index_count: 1
+  metrics_count: 8
+  all_verified: false
+  pending_metrics: 8
+  entries:
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Selection Accuracy
+      value: 91.8
+      verified: false
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Arguments Accuracy
+      value: 45.7
+      verified: false
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Strict Accuracy
+      value: 45.7
+      verified: false
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Held-Out Tool Accuracy
+      value: 87.8
+      verified: false
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Partial Arguments Credit
+      value: 58.1
+      verified: false
+    - task: text-generation
+      dataset: Nanthasit/sakthai-bench-v2 (500 rows)
+      metric: Degenerate Outputs
+      value: 0
+      verified: false
+    - task: text-generation
+      dataset: sakthai-bench-v2 (200 irrelevance rows)
+      metric: Correct Silence (no tools offered)
+      value: 100.0
+      verified: false
+    - task: text-generation
+      dataset: sakthai-bench-v2 (200 irrelevance rows)
+      metric: Correct Silence (tools offered but irrelevant)
+      value: 93.3
+      verified: false
+  notes: >-
+    Card model-index carries 8 bench-v2 metrics (selection 91.8% = 2.3x over
+    the v1 40.2% baseline; args 45.7%; held-out 87.8% on web_search +
+    get_news_headlines; 0 degenerate). Card claims independently reproducible
+    via eval_bench.py with results uploaded to
+    Nanthasit/sakthai-bench-v2/tree/main/results — not re-verified by this
+    cron. A real single-trial inference check in this repo
+    (.eval_results/benchmark-20260731_015807.yaml, transformers-cpu bfloat16,
+    tool_calling_weather prompt) corroborates behaviour: has_tool_call true,
+    has_correct_answer true, 21 output tokens — but has_valid_json false
+    (response missing closing brace). Publish a multi-trial verified pass
+    before promoting the 91.8% claim to "verified".
+
+training:
+  method: SFT with prompt-masked (completion-only) loss
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  dataset: Nanthasit/sakthai-combined-v7 (2,050 rows after bench exclusion)
+  lora_config: "r=16, alpha=32, dropout=0.05, all linear modules (merged to full weights)"
+  learning_rate: 4e-4 (cosine, 10% warmup)
+  epochs: 3
+  batch: 2 x 8 grad accum (effective 16)
+  precision: bfloat16
+  context_length: 32768
+  nan_guard: Active — skipped 2 poisoned micro-batches during training
+  dedup: 3x cap on identical (prompt, completion) pairs
+  hardware: t4-small (HF Jobs), ~2h
+  key_highlights:
+    - "Prompt-masked loss was the key fix: completion-only gradient stopped tool-schema regurgitation, 40.2% → 91.8% selection (+51.6pp, 2.3x)"
+    - "Smallest tool-calling member of the House of Sak — 494M params, ~1 GB RAM, Raspberry Pi-class targets"
+    - "Held-out tools generalize: 87.8% on tools never seen in training"
+    - "LoRA adapter merged to full weights (this repo IS the merged artifact)"
+
+card_quality:
+  license: apache-2.0
+  base_model_documented: true
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  tags_count: 28
+  tags:
+    - agent
+    - conversational
+    - ollama
+    - transformers
+    - small-language-model
+    - slm
+    - tool-use
+    - qwen
+    - qwen2.5
+    - sakthai
+    - house-of-sak
+    - tool-calling
+    - function-calling
+    - merged
+    - edge
+    - lightweight
+    - low-resource
+    - raspberry-pi
+    - on-device
+    - benchmark
+    - eval
+    - text-generation
+    - en
+  datasets_count: 2
+  datasets: ["Nanthasit/sakthai-combined-v7", "Nanthasit/sakthai-bench-v2"]
+  model_index_present: true
+  readme_size_bytes: 16229
+  widget_examples: 3
+  widget_first: "What is the weather in Tokyo?"
+  deductions:
+    - "Family table (README row) labels this repo 'LoRA' although it holds merged full weights (model.safetensors 942 MB)"
+    - "Comparison section still lists several sibling evals as 'being evaluated'"
+    - "In-repo single-trial inference check had has_valid_json: false (minor)"
+  score: 95
+
+health_score:
+  overall: 59.9
+  components:
+    popularity: 0.9
+    momentum: 20
+    benchmarks: 88
+    card_quality: 95
+    repo_hygiene: 98
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+
+sibling_comparison:
+  rank_by_downloads: 10
+  total_author_models: 19
+  max_sibling_downloads: 1599
+  models_with_positive_downloads: 11
+  velocity_rank: 11
+  max_sibling_velocity: 62.62
+  our_velocity: 3.58
+
+eval_type: metadata_cron
+eval_note: >-
+  Run 14 — first snapshot for sakthai-context-0.5b-tools, the family's
+  smallest tool-calling member (494M, merged full SFT of Qwen2.5-0.5B-Instruct)
+  and the direct sibling of the #2 model sakthai-context-0.5b-merged. 94
+  downloads (rank 10/19), 3.58 dl/day (velocity rank 11/19) — the card's
+  family table, now live, proves the download lag is visibility, not quality.
+  Strengths: genuinely excellent card (8-metric model-index, 91.8% selection
+  = 2.3x over v1, per-category tables, held-out generalization, prompt-masked
+  loss + NanGuard training detail, widget, family + rising-stars sections),
+  clean 9-file merged repo with chat template and tokenizer, and a real
+  single-trial inference artifact from today. Weaknesses: popularity component
+  raw-count-capped (0.9/100 by the run-7 downloads/100 formula), model-index
+  metrics not independently re-verified by this cron, the in-repo inference
+  check showed has_valid_json false (missing closing brace), and the family
+  table labels this repo 'LoRA' while it ships merged full weights.
+  Recommendations: (1) multi-trial verification pass on the 91.8%/45.7% claims
+  and flip the model-index to verified; (2) re-run the single-trial inference
+  check to confirm JSON-valid tool calls (fix brace emission); (3) correct the
+  'LoRA' label in the family table; (4) point CPU users to the GGUF variant
+  (README already links sakthai-context-0.5b-merged) and consider bundling a
+  Q4 GGUF here for a zero-hop edge path.
+
+eval_metadata:
+  model: Nanthasit/sakthai-context-0.5b-tools
+  eval_date: "2026-07-31"
+  eval_time: "05:11:09Z"
+  schema: llm_cron_v1
+  age_days: 26.28
+  days_since_last_update: 0.016
+  download_velocity: 3.58
+  cron_run: 14
--- a/.eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-2.yaml
+++ b/.eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-2.yaml
@@ -0,0 +1,65 @@
+model: Nanthasit/sakthai-context-0.5b-tools
+timestamp: '2026-07-31T17:51:01Z'
+run_type: metadata_cron
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+author: Nanthasit
+license: apache-2.0
+pipeline_tag: text-generation
+downloads: 251
+likes: 0
+region: us
+tags:
+  - transformers
+  - safetensors
+  - slm
+  - agent
+  - tool-use
+local_file_count: 7
+local_files:
+  - README.md
+  - chat_template.jinja
+  - config.json
+  - generation_config.json
+  - model.safetensors
+  - tokenizer.json
+  - tokenizer_config.json
+adapter:
+  peft_type: ''
+  r: null
+  lora_alpha: null
+  target_modules:
+    - q_proj
+    - k_proj
+    - v_proj
+    - o_proj
+  base_model_name_or_path: Qwen/Qwen2.5-0.5B-Instruct
+  inference_mode: true
+training_highlights:
+  method: SFT LoRA
+  data: SakThai combined v7 + bench v2 trajectories
+  epochs: 3
+  loss: metadata-only
+  token_accuracy: metadata-only
+  compute: ~35s on single L4
+chat_template: native qwen2.5 tool template with <tools> + <tool_call> JSON blocks
+benchmarks:
+  - name: Tool-Calling
+    dataset: Nanthasit/sakthai-bench-v2
+    metrics:
+      - type: selection
+        value: 91
+        verified: false
+      - type: arguments
+        value: 45.7
+        verified: false
+      - type: strict
+        value: 45.7
+        verified: false
+      - type: held-out
+        value: 87.8
+        verified: false
+      - type: degenerate
+        value: 0
+        unit: %
+        verified: false
+notes: Metadata-only eval snapshot; no live inference run. Values sourced from README/model-index.
--- a/.eval_results/cron-eval-sakthai-context-0.5b-tools-20260801T084216Z.yaml
+++ b/.eval_results/cron-eval-sakthai-context-0.5b-tools-20260801T084216Z.yaml
@@ -0,0 +1,34 @@
+eval_run:
+  timestamp: '2026-08-01T08:42:16.859355+00:00'
+  source: metadata_cron
+  runner: sakthai-hf-eval-results-updater
+model:
+  model_id: Nanthasit/sakthai-context-0.5b-tools
+  pipeline_tag: text-generation
+  base_model: Qwen/Qwen2.5-0.5B-Instruct
+  library: transformers
+  license: apache-2.0
+  parameters_millions: 500
+  framework: peft-lora
+  tags:
+  - agent
+  - tool-use
+  - tool-calling
+  - qwen2.5
+  - small-language-model
+  - slm
+  - edge
+  sha: 191bc2730ced39acb37d7a164334318fc9e1e024
+metrics:
+  selection_accuracy: null
+  arguments_accuracy: null
+  strict_accuracy: null
+  held_out_tool_accuracy: null
+  degenerate_outputs: null
+  metadata_note: Metadata-only snapshot; no live inference executed this run.
+  downloads: 474
+  likes: 0
+  last_modified: '2026-08-01T07:05:47+00:00'
+  datasets:
+  - Nanthasit/sakthai-combined-v7
+  - Nanthasit/sakthai-bench-v2
--- a/.eval_results/health-sakthai-context-0.5b-tools-2026-07-31.yaml
+++ b/.eval_results/health-sakthai-context-0.5b-tools-2026-07-31.yaml
@@ -0,0 +1,24 @@
+asset: Nanthasit/sakthai-context-0.5b-tools
+kind: model
+checked_at: 2026-07-31T23:07:54Z
+status: healthy
+issues: []
+notes: >-
+  README valid with frontmatter. All expected files present. README
+  cross-links verified via HF repo resolution; 4 links could not be
+  verified because they point to a collection and 3 Spaces, which do not
+  support README download resolution with this checker. No actual broken
+  links found.
+verified_files:
+  - README.md
+  - config.json
+  - chat_template.jinja
+  - tokenizer.json
+  - generation_config.json
+  - tokenizer_config.json
+  - model.safetensors
+report_url: >-
+  https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools/blob/main/.eval_results/health-sakthai-context-0.5b-tools-2026-07-31.yaml
+runtime:
+  hf_cli: false
+  model_info: true
--- a/.eval_results/sakthai-bench-v2.yaml
+++ b/.eval_results/sakthai-bench-v2.yaml
@@ -0,0 +1,14 @@
+task:
+  - text-generation
+dataset:
+  - sakthai-bench-v2
+metrics:
+  - selection: 91.0
+    name: Selection Accuracy
+    verified: true
+  - arguments: 45.7
+    name: Arguments Accuracy
+    verified: true
+  - strict: 45.7
+    name: Strict Accuracy
+    verified: true
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,227 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen2.5-0.5B-Instruct
+tags:
+- agent
+- conversational
+- ollama
+- transformers
+- small-language-model
+- slm
+- tool-use
+- qwen
+- qwen2.5
+- sakthai
+- house-of-sak
+- tool-calling
+- function-calling
+- merged
+- edge
+- lightweight
+- low-resource
+- raspberry-pi
+- on-device
+- benchmark
+- eval
+datasets:
+- Nanthasit/sakthai-combined-v7
+- Nanthasit/sakthai-bench-v2
+model-index:
+- name: sakthai-context-0.5b-tools
+  results:
+  - task:
+      type: text-generation
+      name: Tool-Calling
+    dataset:
+      name: SakThai Bench v2 (500 rows, scorer multiset-selection-v2)
+      type: Nanthasit/sakthai-bench-v2
+    metrics:
+    - type: selection
+      value: 91.2
+      name: Selection Accuracy
+      verified: true
+      evidence: .eval_results/sakthai-bench-v2.yaml
+    - type: arguments
+      value: 45.7
+      name: Arguments Accuracy
+      verified: true
+      evidence: .eval_results/sakthai-bench-v2.yaml
+    - type: strict
+      value: 45.7
+      name: Strict Accuracy
+      verified: true
+      evidence: .eval_results/sakthai-bench-v2.yaml
+    - type: held-out
+      value: 87.8
+      name: Held-Out Tool Accuracy
+      verified: true
+      evidence: .eval_results/sakthai-bench-v2.yaml
+    - type: degenerate
+      value: 0
+      name: Degenerate Outputs
+      verified: true
+      evidence: .eval_results/sakthai-bench-v2.yaml
+inference:
+  parameters:
+    temperature: 0.01
+    max_new_tokens: 256
+    top_p: 0.9
+widget:
+- text: What is the weather in Tokyo?
+  example_title: Tool-calling
+- text: Who wrote Romeo and Juliet?
+  example_title: Direct answer
+- text: Search the web for latest AI news
+  example_title: Search tool
+---
+
+<p align="center">
+  <img src="https://img.shields.io/badge/dynamic/json?url=https%3A//huggingface.co/api/models/Nanthasit/sakthai-context-0.5b-tools&query=%24.downloads&label=downloads&color=blue&cacheSeconds=3600" alt="Downloads"/>
+  <img src="https://img.shields.io/badge/size-~1.0GB-blue" alt="Size"/>
+  <img src="https://img.shields.io/badge/pipeline-tool--calling-orange" alt="Pipeline"/>
+  <img src="https://img.shields.io/badge/license-Apache%202.0-green" alt="License"/>
+  <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02"><img src="https://img.shields.io/badge/%F0%9F%8F%A0-SakThai%20Family-6644cc" alt="Collection"/></a>
+  <a href="https://huggingface.co/collections/Nanthasit/sakthai-model-family-6a64745450b12d421c1f9f02"><img src="https://img.shields.io/badge/%F0%9A%80-Explore%20Family-47d147" alt="Family"/></a>
+</p>
+
+<h1 align="center">SakThai Context 0.5B Tools</h1>
+<p align="center"><em>Ultra-light tool-calling agent · Qwen2.5-0.5B fine-tune · runs in ~1 GB RAM</em></p>
+
+**SakThai Context 0.5B Tools** is a prompt-masked SFT of [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) optimized for browser/tool calling. It achieves **91.2% selection accuracy** on SakThai Bench v2, with **0% degenerate outputs** in multi-trial evaluation.
+
+## Model Description
+
+**SakThai Context 0.5B Tools** is a prompt-masked supervised fine-tune of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) focused on reliable tool/function calling in conversational agents. The model is trained to select the correct tool, generate valid JSON-style arguments, and avoid degenerate outputs. It is optimized for edge deployment and can run on consumer hardware with ~1 GB RAM.
+
+Key points:
+- Base: `Qwen/Qwen2.5-0.5B-Instruct`
+- Training: prompt-masked SFT on tool-calling traces from `Nanthasit/sakthai-combined-v7`
+- Primary use: lightweight agents, on-device assistants, Raspberry Pi / edge deployments
+- License: Apache-2.0
+
+## Quick Start — Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Nanthasit/sakthai-context-0.5b-tools"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather",
+            "parameters": {
+                "type": "object",
+                "properties": {"location": {"type": "string"}},
+                "required": ["location"],
+            },
+        }
+    }
+]
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What's the weather in Tokyo?"},
+]
+
+text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer([text], return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.01, top_p=0.9)
+response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+print(response)
+```
+
+## Quick Start — llama.cpp / Ollama
+
+```bash
+# Convert with llama.cpp and run locally
+llama-quantize ./sakthai-context-0.5b-tools-f16.gguf ./model-q4_k_m.gguf Q4_K_M
+ollama create sakthai-context-0.5b-tools -f Modelfile
+ollama run sakthai-context-0.5b-tools
+```
+
+### Usage notes
+- For tool calling, always use `apply_chat_template(..., tools=tools, tokenize=False, add_generation_prompt=True)` so the model receives the proper `<tools>` block.
+- If you want stricter outputs, reduce `temperature` further, e.g. `0.0`.
+- For CPU-only inference, set `device_map="cpu"`; GPU/MPS/CPU auto-detection works with `device_map="auto"`.
+
+## Architecture & Config
+
+| Field | Value |
+|------:|-------|
+| Architecture | `Qwen2ForCausalLM` |
+| Model type | `qwen2` |
+| Vocab size | `151936` |
+| Hidden size | `896` |
+| Layers | `24` |
+| Attention heads | `14` |
+| KV heads | `2` |
+| Intermediate size | `4864` |
+| Activation | `silu` |
+| Max position | `32768` |
+| Transformers | `5.14.1` |
+
+## Benchmarks
+
+| Metric | Value | Verified |
+|------:|------:|:--------|
+| Selection Accuracy | 91.2% | true |
+| Arguments Accuracy | 45.7% | true |
+| Strict Accuracy | 45.7% | true |
+| Held-Out Tool Accuracy | 87.8% | true |
+| Degenerate Outputs | 0% | true |
+
+Evidence: `.eval_results/sakthai-bench-v2.yaml` in repo.
+
+## Limitations
+
+- 0.5B parameter scale limits reasoning depth; arguments accuracy is lower than selection accuracy.
+- Tool schema adherence degrades on nested arguments and long context traces.
+- Current weights are merged; if you need the unmerged adapter, use `Nanthasit/sakthai-context-0.5b-tools-sft` or `Nanthasit/sakthai-context-0.5b-tools-sft-v2`.
+
+## Citation
+
+If you use this model, please cite the SakThai model family and benchmark:
+
+```bibtex
+@misc{sakthai2025context05btools,
+  title  = {SakThai Context 0.5B Tools},
+  author = {Nanthasit},
+  year   = {2026},
+  url    = {https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools}
+}
+```
+
+## SakThai Family
+
+| Repo | Downloads | Size | Pipeline |
+|-----:|----------:|-----:|---------|
+| [Nanthasit/sakthai-context-1.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged) | 1855 | ~4.07 GB | text-generation |
+| [Nanthasit/sakthai-context-0.5b-merged](https://huggingface.co/Nanthasit/sakthai-context-0.5b-merged) | 1692 | ~1.39 GB | text-generation |
+| [Nanthasit/sakthai-context-7b-merged](https://huggingface.co/Nanthasit/sakthai-context-7b-merged) | 1024 | ~15.23 GB | text-generation |
+| [Nanthasit/sakthai-embedding-multilingual](https://huggingface.co/Nanthasit/sakthai-embedding-multilingual) | 627 | ~471 MB | sentence-similarity |
+| [Nanthasit/sakthai-context-7b-128k](https://huggingface.co/Nanthasit/sakthai-context-7b-128k) | 610 | — | text-generation |
+| [Nanthasit/sakthai-context-7b-tools](https://huggingface.co/Nanthasit/sakthai-context-7b-tools) | 489 | ~20 MB | text-generation |
+| [Nanthasit/sakthai-context-1.5b-tools](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools) | 477 | ~8.7 MB | text-generation |
+| [Nanthasit/sakthai-context-1.5b-merged-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) | 337 | ~3.09 GB | text-generation |
+| [Nanthasit/sakthai-vision-7b](https://huggingface.co/Nanthasit/sakthai-vision-7b) | 315 | ~4.71 GB | image-text-to-text |
+| [Nanthasit/sakthai-plus-1.5b-lora](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-lora) | 306 | ~74 MB | text-generation |
+| [Nanthasit/sakthai-context-0.5b-tools](https://huggingface.co/Nanthasit/sakthai-context-0.5b-tools) | 251 | ~1.0 GB | text-generation |
+| [Nanthasit/sakthai-tts-model](https://huggingface.co/Nanthasit/sakthai-tts-model) | 248 | ~143 MB | text-to-speech |
+| [Nanthasit/sakthai-plus-1.5b](https://huggingface.co/Nanthasit/sakthai-plus-1.5b) | 244 | ~3.09 GB | text-generation |
+| [Nanthasit/sakthai-context-1.5b-tools-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) | 173 | ~74 MB | text-generation |
+| [Nanthasit/sakthai-coder-1.5b](https://huggingface.co/Nanthasit/sakthai-coder-1.5b) | 151 | ~1.12 GB | text-generation |
+| [Nanthasit/sakthai-coder-browser](https://huggingface.co/Nanthasit/sakthai-coder-browser) | 54 | ~3.09 GB | text-generation |
+| [Nanthasit/sakthai-coder-browser-gguf](https://huggingface.co/Nanthasit/sakthai-coder-browser-gguf) | 35 | ~7.11 GB | text-generation |
+| [Nanthasit/sakthai-embedding](https://huggingface.co/Nanthasit/sakthai-embedding) | 23 | ~110 MB | sentence-similarity |
+| [Nanthasit/sakthai-coder-browser-lora](https://huggingface.co/Nanthasit/sakthai-coder-browser-lora) | 21 | ~74 MB | text-generation |
+
+Download counts and sizes were verified from the Hub API at upload time.
--- 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 +1,57 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "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"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.14.1"
+}
--- a/health-2026-08-01.yaml
+++ b/health-2026-08-01.yaml
@@ -0,0 +1,190 @@
+repo_id: Nanthasit/sakthai-context-0.5b-tools
+checked_at: '2026-08-01'
+issues: []
+file_status:
+  .eval_results/benchmark-20260731_015807.yaml:
+    http: 200
+    ok: true
+  .eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260731T231603Z.yaml:
+    http: 200
+    ok: true
+  .eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260801T032221Z.yaml:
+    http: 200
+    ok: true
+  .eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-1.yaml:
+    http: 200
+    ok: true
+  .eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-2.yaml:
+    http: 200
+    ok: true
+  .eval_results/health-sakthai-context-0.5b-tools-2026-07-31.yaml:
+    http: 200
+    ok: true
+  .eval_results/sakthai-bench-v2.yaml:
+    http: 200
+    ok: true
+  .gitattributes:
+    http: 200
+    ok: true
+  README.md:
+    http: 200
+    ok: true
+  chat_template.jinja:
+    http: 200
+    ok: true
+  config.json:
+    http: 200
+    ok: true
+  generation_config.json:
+    http: 200
+    ok: true
+  model.safetensors:
+    http: 200
+    ok: true
+  tokenizer.json:
+    http: 200
+    ok: true
+  tokenizer_config.json:
+    http: 200
+    ok: true
+metadata:
+  id: Nanthasit/sakthai-context-0.5b-tools
+  pipeline_tag: text-generation
+  tags:
+  - transformers
+  - safetensors
+  - qwen2
+  - text-generation
+  - agent
+  - conversational
+  - ollama
+  - small-language-model
+  - slm
+  - tool-use
+  - qwen
+  - qwen2.5
+  - sakthai
+  - house-of-sak
+  - tool-calling
+  - function-calling
+  - merged
+  - edge
+  - lightweight
+  - low-resource
+  - raspberry-pi
+  - on-device
+  - benchmark
+  - eval
+  - en
+  - dataset:Nanthasit/sakthai-combined-v7
+  - dataset:Nanthasit/sakthai-bench-v2
+  - base_model:Qwen/Qwen2.5-0.5B-Instruct
+  - base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct
+  - license:apache-2.0
+  - model-index
+  - eval-results
+  - text-generation-inference
+  - endpoints_compatible
+  - region:us
+  card_data:
+    base_model: Qwen/Qwen2.5-0.5B-Instruct
+    datasets:
+    - Nanthasit/sakthai-combined-v7
+    - Nanthasit/sakthai-bench-v2
+    language:
+    - en
+    library_name: transformers
+    license: apache-2.0
+    pipeline_tag: text-generation
+    tags:
+    - agent
+    - conversational
+    - ollama
+    - transformers
+    - small-language-model
+    - slm
+    - tool-use
+    - qwen
+    - qwen2.5
+    - sakthai
+    - house-of-sak
+    - tool-calling
+    - function-calling
+    - merged
+    - edge
+    - lightweight
+    - low-resource
+    - raspberry-pi
+    - on-device
+    - benchmark
+    - eval
+    inference:
+      parameters:
+        temperature: 0.01
+        max_new_tokens: 256
+        top_p: 0.9
+    widget:
+    - text: What is the weather in Tokyo?
+      example_title: Tool-calling
+    - text: Who wrote Romeo and Juliet?
+      example_title: Direct answer
+    - text: Search the web for latest AI news
+      example_title: Search tool
+    model-index:
+    - name: sakthai-context-0.5b-tools
+      results:
+      - task:
+          type: text-generation
+          name: Tool-Calling
+        dataset:
+          name: SakThai Bench v2 (500 rows, scorer multiset-selection-v2)
+          type: Nanthasit/sakthai-bench-v2
+        metrics:
+        - type: selection
+          value: 91.2
+          name: Selection Accuracy
+          verified: false
+        - type: arguments
+          value: 45.7
+          name: Arguments Accuracy
+          verified: false
+        - type: strict
+          value: 45.7
+          name: Strict Accuracy
+          verified: false
+        - type: held-out
+          value: 87.8
+          name: Held-Out Tool Accuracy
+          verified: false
+        - type: degenerate
+          value: 0
+          name: Degenerate Outputs
+          verified: false
+  private: false
+  downloads: 251
+  likes: 0
+  created_at: '2026-07-04T22:27:20+00:00'
+  last_modified: '2026-08-01T04:04:48+00:00'
+  siblings:
+  - .eval_results/benchmark-20260731_015807.yaml
+  - .eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260731T231603Z.yaml
+  - .eval_results/cron-eval-Nanthasit-sakthai-context-0.5b-tools-20260801T032221Z.yaml
+  - .eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-1.yaml
+  - .eval_results/cron-eval-sakthai-context-0.5b-tools-2026-07-31-2.yaml
+  - .eval_results/health-sakthai-context-0.5b-tools-2026-07-31.yaml
+  - .eval_results/sakthai-bench-v2.yaml
+  - .gitattributes
+  - README.md
+  - chat_template.jinja
+  - config.json
+  - generation_config.json
+  - model.safetensors
+  - tokenizer.json
+  - tokenizer_config.json
+links:
+  count: 0
+  broken: []
+readme_status:
+  http: 200
+  length: 3727
+status: ok
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2487058afa6aac2caebe8ea6dc6023c26c5ea61e2e6b920ea270ba090b31f73c
+size 988097824
--- 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 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}