初始化项目，由ModelHub XC社区提供模型

Model: Nanthasit/sakthai-plus-1.5b Source: Original Platform
2026-08-21 08:25:19 +08:00
commit 1fe2da0c55
29 changed files with 153505 additions and 0 deletions
--- a/.eval_results/benchmark-20260731_043634.yaml
+++ b/.eval_results/benchmark-20260731_043634.yaml
@@ -0,0 +1,87 @@
+model: Nanthasit/sakthai-plus-1.5b
+benchmark_ts: '2026-07-31T04:36:34Z'
+backend: llama.cpp-gguf-q4_k_m
+quantization: q4_k_m
+prompt_type: tool_calling_send_email
+prompt_length_chars: 1290
+prompt: '<|im_start|>system
+
+  You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
+
+
+  # Tools
+
+
+  Yo...'
+trials: 3
+total_time_s: 47.56
+input_tokens: 308
+avg_generation_tps: 20.7
+has_tool_call_any: true
+has_tool_call_all: true
+has_valid_json_any: true
+has_valid_json_all: true
+has_correct_answer_any: true
+has_correct_answer_all: true
+trials_detail:
+- seed: 7
+  output_tokens: 63
+  output_length: 231
+  generation_tps: 20.9
+  prompt_tps: 67.0
+  has_tool_call: true
+  has_valid_json: true
+  has_correct_answer: true
+  tool_name: send_email
+  tool_args:
+    to: Beer@Nanthasit.com
+    subject: Plus 1.5B status
+    body: Hi Beer, I wanted to check the benchmark results for the SakThai Plus model.
+      Thanks!
+  response_preview: '<tool_call>
+
+    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
+    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the benchmark results
+    for the SakThai Plus m'
+- seed: 42
+  output_tokens: 65
+  output_length: 243
+  generation_tps: 20.8
+  prompt_tps: 71.0
+  has_tool_call: true
+  has_valid_json: true
+  has_correct_answer: true
+  tool_name: send_email
+  tool_args:
+    to: Beer@Nanthasit.com
+    subject: Plus 1.5B status
+    body: Hi Beer, I wanted to check the results for the SakThai Plus model. Everything
+      looks good so far.
+  response_preview: '<tool_call>
+
+    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
+    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the results for the
+    SakThai Plus model. Ever'
+- seed: 1337
+  output_tokens: 66
+  output_length: 253
+  generation_tps: 20.4
+  prompt_tps: 70.5
+  has_tool_call: true
+  has_valid_json: true
+  has_correct_answer: true
+  tool_name: send_email
+  tool_args:
+    to: Beer@Nanthasit.com
+    subject: Plus 1.5B status
+    body: Hi Beer, I wanted to check the benchmark results for the SakThai Plus model.
+      Everything looks good so far.
+  response_preview: '<tool_call>
+
+    {"name": "send_email", "arguments": "{\"to\": \"Beer@Nanthasit.com\", \"subject\":
+    \"Plus 1.5B status\", \"body\": \"Hi Beer, I wanted to check the benchmark results
+    for the SakThai Plus m'
+device: cpu
+threads: 2
+router_probe_status: 400
+router_probe_error: Model not supported by provider hf-inference
--- a/.eval_results/cron-eval-Nanthasit_sakthai-plus-1.5b-20260801T061747Z.yaml
+++ b/.eval_results/cron-eval-Nanthasit_sakthai-plus-1.5b-20260801T061747Z.yaml
@@ -0,0 +1,30 @@
+eval_results:
+  - task: tool_call_format_adherence
+    task_type: metadata
+    result:
+      score: metadata_only
+      display_name: Metadata-based snapshot
+    dataset:
+      name: metadata
+      split: null
+    metrics:
+      - name: metadata_valid
+        type: metadata
+        value: 1.0
+        higher_is_better: true
+        config: null
+    source:
+      url: https://huggingface.co/Nanthasit/sakthai-plus-1.5b
+      commit: 95450c087e9ca26c3ccf0e06d153e9837ba3ab15
+    model: Nanthasit/sakthai-plus-1.5b
+    created_at: 2026-08-01T06:17:47.707241+00:00
+    evaluator: SakThai-cron
+    notes: |
+      Metadata-only cron update for Nanthasit/sakthai-plus-1.5b.
+      base_model: Qwen/Qwen2.5-1.5B-Instruct
+      pipeline_tag: text-generation
+      license: apache-2.0
+      downloads: 244
+      likes: 0
+      datasets: Nanthasit/sakthai-combined-v7, Nanthasit/SimpleToolCalling
+      tags: tool-calling, function-calling, agent, instruct, finetuned, sft, merged, rsLoRA
--- a/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31-1.yaml
+++ b/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31-1.yaml
@@ -0,0 +1,191 @@
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  downloads: 0
+  likes: 0
+  private: false
+  gated: false
+  last_modified: "2026-07-31T04:40:16.000Z"
+  model_age_days: 0.6961
+  model_type: llm
+  has_weights: true
+
+architecture:
+  base_model_type: qwen2
+  base_architectures: ["Qwen2ForCausalLM"]
+  base_hidden_size: 1536
+  base_num_hidden_layers: 28
+  base_num_attention_heads: 12
+  base_num_key_value_heads: 2
+  base_intermediate_size: 8960
+  base_vocab_size: 151936
+  base_max_position_embeddings: 32768
+  base_total_parameters: 1540000000
+  base_dtype: bfloat16
+  tie_word_embeddings: true
+
+repo_summary:
+  siblings_count: 18
+  total_repo_bytes: 3098931104
+  total_gb: 3.099
+  has_weights: true
+  weight_file_count: 1
+  weight_bytes: 3087467144
+  weight_files: ["model.safetensors"]
+  config_present: true
+  tokenizer_present: true
+  chat_template_present: true
+  readme_present: true
+  readme_size_bytes: 8079
+  weight_note: "Single merged full-weight checkpoint (2.88 GiB, bf16) — no PEFT dependency at inference. Standard Qwen2.5 layout: config.json, generation_config.json, tokenizer.json, tokenizer_config.json, chat_template.jinja, README.md."
+
+benchmarks:
+  model_index_count: 0
+  metrics_count: 9
+  all_verified: false
+  pending_metrics: 6
+  entries:
+    - dataset: lighteval
+      metric: winogrande
+      value: 59.6
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: lighteval
+      metric: gsm8k
+      value: 50.9
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: lighteval
+      metric: hellaswag
+      value: 34.0
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: selection_accuracy
+      value: 84.8
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: arguments_accuracy
+      value: 33.7
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: strict_accuracy
+      value: 33.7
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: tool_call_success
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — send_email prompt, 3/3 tool calls"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: valid_json
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — 3/3 valid JSON tool args"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: correct_answer
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — 3/3 correct answers, avg 20.7 tps (CPU, 2 threads)"
+  notes: >
+    README frontmatter has NO model-index (model_index_count: 0) despite
+    .eval_results/ carrying three benchmark sources: lighteval + sakthai-bench-v2
+    (all unverified) and a fresh 2026-07-31 3-trial llama.cpp q4_k_m run that
+    passed tool-calling 3/3 (tool_call, valid JSON, correct answer). Card text
+    still says 'Benchmarks are pending' — stale relative to repo state.
+
+training:
+  dataset: Nanthasit/sakthai-combined-v10
+  dataset_size: 2962
+  dataset_note: "v7 + v8 combined (2,962 rows, published as sakthai-combined-v10); card also cites sakthai-combined-v7"
+  training_method: "rsLoRA (rank-stabilized) → merged to full weights"
+  eval_split: "none documented on card (benchmarks pending)"
+  lora_config:
+    r: 16
+    alpha: 32
+    dropout: 0.05
+    target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]
+  optimizer: "AdamW (8-bit)"
+  learning_rate: 0.0002
+  epochs: 3
+  precision: bf16
+  hardware: "Free T4 GPU (Kaggle / Colab / HF Inference), $0 budget"
+  framework: "TRL + Transformers"
+  key_improvements:
+    - "rsLoRA instead of standard LoRA — better rank utilization"
+    - "All 7 linear modules adapted (vs 4 in v1)"
+    - "Dropout reduced 0.1 → 0.05"
+    - "48% more training data (v7 + v8)"
+    - "Merged full-weight checkpoint — no PEFT dependency at inference"
+
+card_quality:
+  license: apache-2.0
+  base_model_documented: true
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags_count: 12
+  tags: [qwen2.5, sakthai, house-of-sak, tool-calling, function-calling, agent, instruct, finetuned, sft, rslora, text-generation, merged]
+  datasets_cited: ["Nanthasit/sakthai-combined-v7", "Nanthasit/sakthai-combined-v10"]
+  model_index_present: false
+  readme_size_bytes: 8079
+  widget_example: "none (no widget block in frontmatter)"
+  deductions:
+    - "README states 'Benchmarks are pending' but .eval_results/ already carries lighteval + sakthai-bench-v2 scores (unverified) and a verified 3/3 llama.cpp tool-calling run — card text lags repo state"
+    - "No model-index or widget in README frontmatter — metrics will not render on the Hub widget"
+    - "0 downloads / 0 likes — brand-new (created 2026-07-30), family table lists it as 'New'"
+  score: 78
+
+health_score:
+  overall: 38.2
+  components:
+    popularity: 0
+    momentum: 0
+    benchmarks: 33.3
+    card_quality: 78
+    repo_hygiene: 95
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+
+sibling_comparison:
+  rank_by_downloads: 12
+  total_author_models: 19
+  max_sibling_downloads: 1599
+  models_with_positive_downloads: 11
+  velocity_rank: 12
+  max_sibling_velocity: 62.56
+  our_velocity: 0.0
+
+eval_type: metadata_cron
+eval_note: >
+  First cron eval snapshot for sakthai-plus-1.5b (run 16 of hf-eval-updater).
+  The next-generation SakThai tool-calling flagship: Qwen2.5-1.5B-Instruct
+  rsLoRA fine-tune (r=16, alpha=32, dropout=0.05) across all 7 linear modules
+  on sakthai-combined-v10 (v7+v8, 2,962 rows), merged to a full bf16
+  checkpoint (2.88 GiB). Repo hygiene is excellent (95/100) and config is a
+  clean Qwen2-1.5B (28 layers, 12 heads / 2 KV, 32K context). The one verified
+  benchmark — a 2026-07-31 3-trial llama.cpp q4_k_m tool-calling run — passed
+  3/3 (tool call, valid JSON, correct answer, 20.7 tps). Honest caveats:
+  README claims 'benchmarks pending' while .eval_results/ already holds 6
+  unverified lighteval + sakthai-bench-v2 numbers, and the card has no
+  model-index/widget. Brand-new model: 0 downloads, velocity 0 — sits at
+  downloads rank 12/19 (11 siblings positive). Next cycle: run
+  sakthai-bench-v2 properly, add model-index + widget to the card, and update
+  the 'pending' benchmark text to match repo state.
+
+eval_metadata:
+  model: Nanthasit/sakthai-plus-1.5b
+  eval_date: "2026-07-31"
+  eval_time: "05:40:24Z"
+  schema: llm_cron_v1
+  age_days: 0.6961
+  days_since_last_update: 0.0473
+  download_velocity: 0.0
+  cron_run: 16
--- a/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31-2.yaml
+++ b/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31-2.yaml
@@ -0,0 +1,200 @@
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  downloads: 244
+  likes: 0
+  private: false
+  gated: false
+  last_modified: "2026-07-31T11:09:05.000Z"
+  model_age_days: 1.00
+  model_type: llm
+  has_weights: true
+
+architecture:
+  base_model_type: qwen2
+  base_architectures: ["Qwen2ForCausalLM"]
+  base_hidden_size: 1536
+  base_num_hidden_layers: 28
+  base_num_attention_heads: 12
+  base_num_key_value_heads: 2
+  base_intermediate_size: 8960
+  base_vocab_size: 151936
+  base_max_position_embeddings: 32768
+  base_total_parameters: 1540000000
+  base_dtype: bfloat16
+  tie_word_embeddings: true
+
+repo_summary:
+  siblings_count: 20
+  total_repo_bytes: 3098940902
+  total_gb: 2.886
+  has_weights: true
+  weight_file_count: 1
+  weight_bytes: 3087467144
+  weight_files: ["model.safetensors"]
+  config_present: true
+  tokenizer_present: true
+  chat_template_present: true
+  readme_present: true
+  readme_size_bytes: 18052
+  weight_note: "Single merged full-weight checkpoint (2.88 GiB, bf16) — no PEFT dependency at inference. Standard Qwen2.5 layout: config.json, generation_config.json, tokenizer.json, tokenizer_config.json, chat_template.jinja, README.md."
+
+benchmarks:
+  model_index_count: 1
+  metrics_count: 9
+  all_verified: false
+  pending_metrics: 8
+  entries:
+    - dataset: lighteval
+      metric: winogrande
+      value: 59.6
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: lighteval
+      metric: gsm8k
+      value: 50.9
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: lighteval
+      metric: hellaswag
+      value: 34.0
+      verified: false
+      note: "entry in .eval_results/lighteval.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: selection_accuracy
+      value: 84.8
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: arguments_accuracy
+      value: 33.7
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: sakthai-bench-v2
+      metric: strict_accuracy
+      value: 33.7
+      verified: false
+      note: "entry in .eval_results/sakthai-bench-v2.yaml — not re-run, unverified"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: tool_call_success
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — send_email prompt, 3/3 tool calls"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: valid_json
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — 3/3 valid JSON tool args"
+    - dataset: llama.cpp tool-calling (3-trial, q4_k_m)
+      metric: correct_answer
+      value: 1.0
+      verified: true
+      note: ".eval_results/benchmark-20260731_043634.yaml — 3/3 correct answers, avg 20.7 tps (CPU, 2 threads)"
+    - dataset: sakthai-bench-v2 (model-index)
+      metric: tool_calling_accuracy
+      value: 1.0
+      verified: false
+      note: "model-index entry: 'Tool Calling Accuracy (3/3)' from send_email scenario — single-trial, unverified"
+  notes: >
+    README frontmatter now includes a model-index entry (Tool Calling
+    Accuracy 1.0 on send_email scenario, unverified). 3 additional unverified
+    lighteval scores (winogrande 59.6, gsm8k 50.9, hellaswag 34.0) and
+    3 sakthai-bench-v2 scores (selection 84.8, arguments 33.7, strict 33.7)
+    exist in .eval_results/ but are NOT in the model-index. One verified
+    3-trial llama.cpp q4_k_m tool-calling run (3/3, 20.7 tps) is present.
+    Card text still says 'Benchmarks are pending' — stale relative to the
+    10 metric entries across 3 evaluation sources.
+
+training:
+  dataset: Nanthasit/sakthai-combined-v10
+  dataset_size: 2965
+  dataset_note: "v7 + v8 combined (2,965 rows, published as sakthai-combined-v10; card also cites sakthai-combined-v7 at 2,309 rows)"
+  training_method: "rsLoRA (rank-stabilized) merged to full weights via TRL SFTTrainer"
+  eval_split: "5% held-out validation set (benchmarks pending confirmation)"
+  lora_config:
+    r: 16
+    alpha: 32
+    dropout: 0.05
+    target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]
+  optimizer: "AdamW (8-bit)"
+  learning_rate: 0.0002
+  epochs: 3
+  precision: bf16
+  hardware: "Free T4 GPU (Kaggle / Colab / HF Inference), $0 budget"
+  framework: "TRL + Transformers"
+  key_improvements:
+    - "rsLoRA instead of standard LoRA — better rank utilization"
+    - "All 7 linear modules adapted (vs 4 in v1)"
+    - "Dropout reduced 0.1 to 0.05"
+    - "48% more training data (v7 + v8)"
+    - "Merged full-weight checkpoint — no PEFT dependency at inference"
+
+card_quality:
+  license: apache-2.0
+  base_model_documented: true
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags_count: 19
+  tags: [qwen2.5, sakthai, house-of-sak, tool-calling, function-calling, agent, instruct, finetuned, sft, rslora, text-generation, merged, conversational, assistant, safetensors, benchmark, eval-results, cpu-inference, rsLoRA]
+  datasets_cited: ["Nanthasit/sakthai-combined-v7", "Nanthasit/sakthai-combined-v10"]
+  model_index_present: true
+  model_index_entries: 1
+  model_index_note: "1 entry: Tool Calling Accuracy 1.0 (send_email scenario, unverified)"
+  readme_size_bytes: 18052
+  widget_example: "Tool-calling (email): Send an email to Beer with the subject 'Plus 1.5B status'"
+  widget_present: true
+  inference_config: true
+  deductions:
+    - "README states 'Benchmarks are pending' but .eval_results/ already carries 10 metric entries across 3 evaluation sources — card text lags repo state"
+    - "model-index has only 1 of 10 available metrics — 9 unindexed, so they don't render on the Hub widget"
+    - "lighteval scores (winogrande, gsm8k, hellaswag) and sakthai-bench-v2 scores all marked unverified — need multi-trial re-run"
+  score: 85
+
+health_score:
+  overall: 64.2
+  components:
+    popularity: 2.4
+    momentum: 100.0
+    benchmarks: 50.0
+    card_quality: 85.0
+    repo_hygiene: 95.0
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+
+sibling_comparison:
+  rank_by_downloads: 13
+  total_author_models: 22
+  max_sibling_downloads: 1855
+  models_with_positive_downloads: 17
+  velocity_rank: 3
+  max_sibling_velocity: 330.4
+  our_velocity: 244.0
+
+eval_type: metadata_cron
+eval_note: >
+  Re-eval (run 27) for sakthai-plus-1.5b. Since first eval (18h ago):
+  0 to 244 downloads (+244), velocity 244.0/day (3rd fastest among 19
+  models). Health score improved from 38.2 to 64.2 (+26.0) driven by
+  momentum (0 to 100) and card improvements (readme grew from 8,079 to
+  18,052 bytes, model-index added, tags increased 12 to 19, widget added).
+  Card still claims 'Benchmarks are pending' despite 10 metric entries in
+  .eval_results/ — this is the most impactful improvement opportunity.
+  Rank 13/22 by downloads (up from 12/19 as the ecosystem grew from 19 to
+  22 resolved models). Next cycle: reconcile card text with .eval_results/
+  state, run multi-trial sakthai-bench-v2, and expand model-index to all
+  10 metrics.
+
+eval_metadata:
+  model: Nanthasit/sakthai-plus-1.5b
+  eval_date: "2026-07-31"
+  eval_time: "23:00:00Z"
+  schema: llm_cron_v1
+  age_days: 1.00
+  days_since_last_update: 0.72
+  download_velocity: 244.0
+  cron_run: 27
--- a/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31T21:15:37Z.yaml
+++ b/.eval_results/cron-eval-sakthai-plus-1.5b-2026-07-31T21:15:37Z.yaml
@@ -0,0 +1,43 @@
+eval_type: metadata_cron
+result_type: metadata
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  license: apache-2.0
+  repo_sha: bc3ae9206427d2055c3aa2dc2844cad5c70ce541
+  last_modified: '2026-07-31T17:43:41+00:00'
+repository_metrics:
+  downloads: 244
+  likes: 0
+  tags_count: 32
+  model_index_present: true
+download_velocity:
+  collected_at: '2026-07-31T21:15:37Z'
+  total_downloads: 244
+  note: Snapshot only; not time-series velocity.
+adapter_details:
+  peft_type: NONE
+  adapter_size_bytes: 0
+  adapter_size_human: N/A
+inference_assessment:
+  standalone_inference: false
+  requires_merge: false
+  serverless_inference: false
+  local_inference: false
+  recommended_path: Enable serverless inference on HF Hub or convert to GGUF for llama.cpp.
+card_highlights:
+  tags:
+  - transformers
+  - safetensors
+  - qwen2
+  - text-generation
+  - qwen2.5
+  - sakthai
+  - house-of-sak
+  - tool-calling
+  task_type: text-generation
+  language:
+  - en
+notes: Metadata-only snapshot because inference providers reject this model and local
+  inference is blocked by sandbox memory limits.
--- a/.eval_results/cron-eval-sakthai-plus-1.5b-20260801T0217Z.yaml
+++ b/.eval_results/cron-eval-sakthai-plus-1.5b-20260801T0217Z.yaml
@@ -0,0 +1,41 @@
+schema_version: metadata-v1
+result_type: metadata
+type: metadata_cron
+timestamp: '2026-08-01T02:17:00Z'
+model_id: Nanthasit/sakthai-plus-1.5b
+commit_sha: c311c66c59663ecd92b1e79193943478b307a2e1
+last_modified: '2026-07-31 23:32:20+00:00'
+downloads: 244
+likes: 0
+license: apache-2.0
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+pipeline_tag: text-generation
+framework: transformers
+tags:
+- transformers
+- safetensors
+- qwen2
+- text-generation
+- qwen2.5
+- tool-calling
+- function-calling
+- agent
+- instruct
+- finetuned
+- sft
+- merged
+- conversational
+- rsLoRA
+- dataset:Nanthasit/sakthai-combined-v7
+- dataset:Nanthasit/sakthai-combined-v10
+- dataset:Nanthasit/SimpleToolCalling
+config_highlights:
+  model_type: qwen2
+  architectures:
+  - Qwen2ForCausalLM
+  torch_dtype: float32
+  model_validation: sha_matched
+eval_context:
+  existing_eval_count_before: 13
+  new_file_name: .eval_results/cron-eval-sakthai-plus-1.5b-20260801T0217Z.yaml
+  source: hf-eval-updated cron metadata run
--- a/.eval_results/cron-eval-sakthai-plus-1.5b-20260801T114529Z.yaml
+++ b/.eval_results/cron-eval-sakthai-plus-1.5b-20260801T114529Z.yaml
@@ -0,0 +1,108 @@
+eval_id: cron-eval-sakthai-plus-1.5b-20260801T114529Z
+model_id: Nanthasit/sakthai-plus-1.5b
+timestamp: "2026-08-01T11:45:29Z"
+result_type: metadata
+source: metadata_cron
+status: uploaded
+
+model_meta:
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  license: apache-2.0
+  tags:
+    - transformers
+    - safetensors
+    - qwen2.5
+    - sakthai
+    - house-of-sak
+    - tool-calling
+    - function-calling
+    - agent
+    - instruct
+    - finetuned
+    - sft
+    - merged
+    - conversational
+    - assistant
+    - cpu-inference
+    - rsLoRA
+    - benchmark
+    - eval-results
+    - llama-cpp
+  datasets:
+    - Nanthasit/sakthai-combined-v11
+    - Nanthasit/SimpleToolCalling
+  repo_type: model
+  sha: 412d38d60e1727a6586d0e7f5b30426b557824ab
+  last_modified: "2026-08-01T11:45:32Z"
+
+metrics:
+  downloads: 297
+  likes: 0
+
+model_index:
+  - task:
+      type: text-generation
+      name: Tool-Calling Accuracy
+    dataset:
+      name: llama.cpp tool-calling (3-trial, q4_k_m)
+      type: custom
+    metrics:
+      - name: Tool Call Success Rate
+        type: tool_call_success
+        value: 1
+        verified: false
+      - name: Valid JSON Arguments
+        type: valid-json
+        value: 1
+        verified: false
+      - name: Correct Answer Rate
+        type: correct-answer
+        value: 1
+        verified: false
+      - name: Selection Accuracy
+        type: selection-accuracy
+        value: 84.8
+        verified: false
+      - name: Arguments Accuracy
+        type: arguments-accuracy
+        value: 33.7
+        verified: false
+      - name: Strict Accuracy
+        type: strict-accuracy
+        value: 33.7
+        verified: false
+  - task:
+      type: text-generation
+      name: Commonsense Reasoning
+    dataset:
+      name: lighteval
+      type: lighteval
+    metrics:
+      - name: WinoGrande (WSC)
+        type: winogrande
+        value: 59.6
+        verified: false
+      - name: HellaSwag
+        type: hellaswag
+        value: 34.0
+        verified: false
+      - name: GSM8K
+        type: gsm8k
+        value: 50.9
+        verified: false
+
+config_highlights:
+  inference_parameters:
+    temperature: 0.3
+    max_new_tokens: 256
+    top_p: 0.9
+  chat_template: Qwen2.5 tool-calling style with XML <tool_call> blocks
+  quantization_notes: GGUF/compatible; cpu-inference capable
+  adapter_only: false
+  requires_base: false
+
+health:
+  verified: false
+  notes: metadata-only snapshot; no live inference.
--- a/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-2.yaml
+++ b/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-2.yaml
@@ -0,0 +1,97 @@
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  downloads: 0
+  likes: 0
+  private: false
+  gated: false
+  created: 2026-07-30T13:02:40.000Z
+  last_modified: 2026-07-30T22:36:19.000Z
+  model_age_days: 0.4035
+  model_type: llm
+  has_weights: true
+
+architecture:
+  model_type: qwen2
+  architectures: ["Qwen2ForCausalLM"]
+  hidden_size: 1536
+  num_hidden_layers: 28
+  num_attention_heads: 12
+  num_key_value_heads: 2
+  intermediate_size: 8960
+  vocab_size: 151936
+  max_position_embeddings: 32768
+  total_parameters: 1543714304
+  dtype: bfloat16
+
+repo_summary:
+  siblings_count: 11
+  total_repo_bytes: 3098901671
+  total_gb: 2.886
+  has_weights: true
+  weight_file_count: 1
+  weight_bytes: 3087467144
+  config_present: true
+  readme_size_bytes: 6249
+
+benchmarks:
+  model_index_count: 1
+  metrics_count: 2
+  all_verified: false
+  pending_metrics: 1
+  entries:
+  - task: Tool-Calling
+    dataset: SakThai Bench v2 (500 rows, scorer multiset-selection-v2)
+    metrics:
+      - name: Selection Accuracy
+        value: pending
+      - name: Degenerate Rate
+        value: 0
+
+card_quality:
+  license: apache-2.0
+  base_model_documented: true
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags_count: 10
+  tags: ["qwen2.5", "sakthai", "plus", "tool-calling", "conversational", "function-calling", "merged", "rslor", "house-of-sak", "family"]
+  datasets_count: 2
+  datasets: ["Nanthasit/sakthai-combined-v7", "Nanthasit/sakthai-combined-v8"]
+  model_index_present: true
+  readme_size_bytes: 6249
+  deductions: []
+  score: 100
+
+health_score:
+  overall: 34
+  components:
+    popularity: 0
+    momentum: 0
+    benchmarks: 0
+    card_quality: 100
+    repo_hygiene: 90
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+
+sibling_comparison:
+  rank_by_downloads: 15
+  total_author_models: 19
+  max_sibling_downloads: 1599
+  models_with_positive_downloads: 12
+  velocity_rank: 15
+  max_sibling_velocity: 3962.83
+  our_velocity: 0.0
+
+eval_metadata:
+  model: Nanthasit/sakthai-plus-1.5b
+  eval_date: 2026-07-30
+  eval_time: 22:43:40Z
+  schema: llm_cron
+  age_days: 0.4035
+  days_since_last_update: 0.0051
+  download_velocity: 0.0
--- a/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-3.yaml
+++ b/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-3.yaml
@@ -0,0 +1,136 @@
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  slug: sakthai-plus-1.5b
+  model_type: text-generation
+  created: 2026-07-30 13:02:40+00:00
+  last_modified: N/A
+  age_days: 0.4
+  days_since_update: N/A
+
+popularity:
+  downloads: 0
+  likes: 0
+  download_rank: 13/19
+  rank_pct: 32
+  max_sibling_downloads: 1599
+  score: 0
+
+momentum:
+  velocity_dl_per_day: 0.0
+  max_sibling_velocity: 0.0
+  velocity_rank: 13/12
+  score: 0
+  source: blended_ratio_rank
+
+files:
+  model_safetensors: 3087467144
+  file_count: 12
+  total_size_bytes: 3098914639
+  total_size_gb: 2.89
+  has_weights: true
+  has_safetensors: true
+  has_gguf: false
+
+card_content:
+  pipeline_tag: text-generation
+  library_name: transformers
+  license: apache-2.0
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags_count: 10
+  tags:
+    - qwen2.5
+    - sakthai
+    - plus
+    - tool-calling
+    - conversational
+    - function-calling
+    - merged
+    - rslor
+    - house-of-sak
+    - family
+  datasets:
+    - Nanthasit/sakthai-combined-v7
+    - Nanthasit/sakthai-combined-v8
+architecture:
+  model_type: qwen2
+  hidden_size: 1536
+  intermediate_size: 8960
+  num_hidden_layers: 28
+  num_attention_heads: 12
+  num_key_value_heads: 2
+  vocab_size: 151936
+  max_position_embeddings: 32768
+  architectures: ['Qwen2ForCausalLM']
+  dtype: bfloat16
+  parameters: N/A  # safetensors metadata missing
+
+benchmarks:
+  has_model_index: false
+  has_eval_results: true
+  eval_results:
+    - dataset: SakThai Bench v2
+      metric: Selection Accuracy
+      value: pending
+      verified: false
+    - dataset: SakThai Bench v2
+      metric: Degenerate Rate
+      value: 0
+      verified: false
+  score: 0
+  note: No verified benchmarks - all eval results are unverified
+
+assessment:
+  health_score:
+    overall: 35
+    components:
+      popularity_weight_20: 0
+      momentum_weight_20: 0
+      benchmarks_weight_25: 0
+      card_quality_weight_20: 100
+      repo_hygiene_weight_15: 100
+    breakdown:
+      popularity: 0/100 at 20%
+      momentum: 0/100 at 20%
+      benchmarks: 0/100 at 25%
+      card_quality: 100/100 at 20%
+      hygiene: 100/100 at 15%
+
+  assessment_text: >
+    Very new model (0.4 days old). Zero downloads so far. Architecture is Qwen2-based
+    1.5B with 28 layers, 12 attention heads, GQA (2 KV heads), 1536 hidden size,
+    32768 context window. bfloat16 weights. Appears as a fine-tune of
+    Qwen/Qwen2.5-1.5B-Instruct for tool-calling/conversational use.
+    Card quality is strong (apache-2.0 license, base model documented, 10 tags,
+    2 datasets). No verified benchmarks yet. Popularity and momentum are at 0
+    since the model was just uploaded today.
+
+  weight_status: PRESENT
+  skeleton: false
+  note: First health check for this model. No delta comparison available.
+
+sibling_comparison:
+  total_siblings: 18
+  top_siblings:
+    - id: Nanthasit/sakthai-context-1.5b-merged
+      downloads: 1599
+      likes: 0
+    - id: Nanthasit/sakthai-context-0.5b-merged
+      downloads: 1370
+      likes: 0
+    - id: Nanthasit/sakthai-context-7b-merged
+      downloads: 744
+      likes: 0
+    - id: Nanthasit/sakthai-context-7b-128k
+      downloads: 506
+      likes: 0
+    - id: Nanthasit/sakthai-context-7b-tools
+      downloads: 399
+      likes: 0
+
+eval_metadata:
+  model: Nanthasit/sakthai-plus-1.5b
+  date: 2026-07-30
+  version: 1.0
+  source: cron-health-check
+  schema: llm_cron
+  first_run: true
--- a/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-4.yaml
+++ b/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-4.yaml
@@ -0,0 +1,167 @@
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  license: apache-2.0
+  created_at: "2026-07-30T13:02:40.000Z"
+  last_modified: "2026-07-30T22:54:44.000Z"
+  model_type: qwen2
+  architectures:
+    - Qwen2ForCausalLM
+
+architecture:
+  total_params: 1543714304
+  param_dtype: BF16
+  param_label: "1.54B"
+  hidden_size: null
+  num_layers: null
+  num_attention_heads: null
+  vocab_size: null
+
+popularity:
+  downloads: 0
+  likes: 0
+  age_days: 0.414
+  days_since_update: 0.003
+  velocity_dl_per_day: 0.0
+  max_author_downloads: 1599
+  author_rank: 13
+  author_model_count: 19
+
+repo_summary:
+  has_weights: true
+  weight_bytes: 3087467144
+  weight_files: 1
+  total_repo_bytes: 3098922685
+  total_gb: 2.89
+  used_storage_bytes: 6186356180
+  storage_ratio: 2.0
+  sibling_count: 14
+
+files:
+  - name: model.safetensors
+    size: 3087467144
+    type: weight
+  - name: config.json
+    size: 1373
+    type: config
+  - name: tokenizer.json
+    size: 11421892
+    type: tokenizer
+  - name: tokenizer_config.json
+    size: 694
+    type: config
+  - name: generation_config.json
+    size: 242
+    type: config
+  - name: README.md
+    size: 6249
+    type: doc
+  - name: chat_template.jinja
+    size: 2507
+    type: template
+  - name: .gitattributes
+    size: 1570
+    type: meta
+
+card_content:
+  license: apache-2.0
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags:
+    - qwen2.5
+    - sakthai
+    - plus
+    - tool-calling
+    - conversational
+    - function-calling
+    - merged
+    - rslor
+    - house-of-sak
+    - family
+  datasets:
+    - Nanthasit/sakthai-combined-v7
+    - Nanthasit/sakthai-combined-v8
+  library_name: transformers
+  pipeline_tag: text-generation
+  readme_bytes: 6249
+
+benchmarks:
+  has_model_index: true
+  metric_count: 2
+  all_verified: false
+  all_pending: false
+  model_index:
+    - task: Tool-Calling
+      dataset: Nanthasit/sakthai-bench-v2
+      metrics:
+        - name: Selection Accuracy
+          type: selection
+          value: pending
+          verified: false
+
+sibling_comparison:
+  same_pipeline_models: 13
+  max_sibling_downloads: 1599
+  max_sibling_velocity: 63.26
+  sibling_models:
+    - id: Nanthasit/sakthai-context-1.5b-merged
+      downloads: 1599
+    - id: Nanthasit/sakthai-context-0.5b-merged
+      downloads: 1370
+    - id: Nanthasit/sakthai-context-7b-merged
+      downloads: 744
+    - id: Nanthasit/sakthai-context-7b-128k
+      downloads: 506
+    - id: Nanthasit/sakthai-context-7b-tools
+      downloads: 399
+    - id: Nanthasit/sakthai-context-1.5b-tools
+      downloads: 349
+    - id: Nanthasit/sakthai-vision-7b
+      downloads: 186
+    - id: Nanthasit/sakthai-context-0.5b-tools
+      downloads: 94
+    - id: Nanthasit/sakthai-coder-1.5b
+      downloads: 93
+    - id: Nanthasit/sakthai-context-1.5b-tools-v2
+      downloads: 0
+    - id: Nanthasit/sakthai-context-1.5b-merged-v2
+      downloads: 0
+    - id: Nanthasit/sakthai-plus-1.5b-lora
+      downloads: 0
+    - id: Nanthasit/sakthai-plus-1.5b-coder
+      downloads: 0
+
+assessments:
+  is_skeleton: false
+  has_weights: true
+  first_run: true
+
+health_score:
+  final_score: 42
+  components:
+    popularity: 0
+    momentum: 0
+    benchmarks: 40
+    card_quality: 100
+    repo_hygiene: 80
+  weights:
+    popularity: 0.20
+    momentum: 0.20
+    benchmarks: 0.25
+    card_quality: 0.20
+    repo_hygiene: 0.15
+  scoring_notes:
+    - "First health check for this model — no delta computed"
+    - "Zero downloads/likes — brand new model uploaded today"
+    - "Benchmarks are all 'pending' — not yet verified"
+    - "2.0x storage ratio suggests git history bloat (usedStorage vs actual sum)"
+    - "Card quality scores 100/100 — license, base_model, tags, datasets all present"
+    - "Repo hygiene -20 due to 2.0x storage ratio"
+
+eval_metadata:
+  generated_at: "2026-07-30T22:58:35Z"
+  generator: sakthai-model-health-check cron
+  model: sakthai-plus-1.5b
+  host: linux
+  source: hf_api
--- a/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-v2.yaml
+++ b/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30-v2.yaml
@@ -0,0 +1,153 @@
+# Health Check: Nanthasit/sakthai-plus-1.5b
+# Generated: 2026-07-30T22:52:00+00:00
+
+target_model:
+  id: Nanthasit/sakthai-plus-1.5b
+  scanned_at: '2026-07-30T22:52:00+00:00'
+
+popularity:
+  downloads: 0
+  likes: 0
+  last_modified: '2026-07-30T22:48:48.000Z'
+  created_at: '2026-07-30T13:02:40.000Z'
+  age_days: 0
+  hours_since_creation: 9.8
+  download_velocity: 0.0
+  download_growth_rate: 0.0
+
+model_type:
+  pipeline_tag: text-generation
+  library_name: transformers
+  architecture: Qwen2ForCausalLM
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  license: apache-2.0
+  type: Safetensors (full weights)
+
+config_details:
+  hidden_size: 1536
+  num_attention_heads: 12
+  num_hidden_layers: 28
+  num_key_value_heads: 2
+  intermediate_size: 8960
+  max_position_embeddings: 32768
+  vocab_size: 151936
+  torch_dtype: bfloat16
+  tie_word_embeddings: true
+  use_cache: true
+  transformers_version: '5.14.1'
+  generation_defaults:
+    temperature: 0.7
+
+files_inventory:
+  model.safetensors: 3087467144 bytes (2.87 GB)
+  config.json: 1373 bytes
+  tokenizer.json: 11421892 bytes (10.89 MB)
+  tokenizer_config.json: 694 bytes
+  generation_config.json: 242 bytes
+  chat_template.jinja: 2507 bytes
+  README.md: 6249 bytes
+  .gitattributes: 1570 bytes
+  .eval_results/sakthai-plus-1.5b-health.yaml: 4016 bytes
+  .eval_results/health-check-sakthai-plus-1.5b-2026-07-30.yaml: 2416 bytes
+  .eval_results/health-check-sakthai-plus-1.5b-2026-07-30-2.yaml: 2277 bytes
+  .eval_results/health-check-sakthai-plus-1.5b-2026-07-30-3.yaml: 3365 bytes
+  .eval_results/health-check-sakthai-plus-1.5b-2026-07-31.yaml: 4259 bytes
+
+storage:
+  model_weight_bytes: 3087467144
+  total_repo_bytes: 3099415512
+  total_repo_gb: 2.89
+  note: 'All files present and valid. No orphaned artifacts.'
+
+inference_available: false
+inference_reason: "Safetensors weights present and eligible, but serverless inference not yet enabled on the HF Hub. Manual inference can be run via Transformers locally."
+inference_eligible: true
+
+tags:
+  - qwen2.5
+  - sakthai
+  - plus
+  - tool-calling
+  - conversational
+  - function-calling
+  - merged
+  - rslor
+  - house-of-sak
+  - family
+
+datasets:
+  - Nanthasit/sakthai-combined-v7
+  - Nanthasit/sakthai-combined-v8
+
+benchmarks:
+- name: sakthai-bench-v2
+  dataset: SakThai Bench v2 (500 rows, scorer multiset-selection-v2)
+  metrics:
+    selection_accuracy: pending
+    degenerate_rate: 0
+  verified: false
+
+card_quality:
+  has_readme: true
+  readme_size_bytes: 6249
+  has_yaml_metadata: true
+  has_widget: true
+  has_benchmarks: true
+  has_base_model: true
+  has_datasets: true
+  has_license: true
+
+sibling_analysis:
+  total_siblings: 13
+  hidden_eval_files: 5
+  dev_artifact_count: 0
+  note: 'Clean repo — no orphaned dev artifacts or junk files'
+
+comparison:
+  target_rank: 15
+  target_rank_by_velocity: 15
+  total_in_author_set: 19
+  download_share_percent: 0.0
+  note: 'Brand new model (same-day). Ranked 15/19 among Nanthasit models by downloads. Above: sakthai-context-1.5b-tools-v2 (0 dl), Below: sakthai-plus-1.5b-lora (0 dl)'
+
+assessment:
+  status: good
+  score: 72
+  breakdown:
+    repo_integrity: 100
+    config_validity: 100
+    documentation: 80
+    inference_availability: 0
+    traffic_momentum: 0
+    benchmark_coverage: 50
+  strengths:
+  - Full safetensors weights present and valid (~2.87 GB)
+  - Clean repo with no orphaned dev artifacts
+  - Complete config and tokenizer files
+  - Model card with YAML metadata, tags, benchmarks, and widget
+  - Based on Qwen2.5-1.5B-Instruct (strong base model)
+  - Apache 2.0 license
+  concerns:
+  - Zero downloads and likes (brand new model — expected)
+  - Benchmarks show 'pending' for selection accuracy
+  - Serverless inference not yet enabled
+  - Extra .eval_results files accumulate on the repository (5 files so far)
+  recommendations:
+  - Enable serverless inference once model is verified
+  - Run and publish actual benchmark results (replace 'pending')
+  - Consolidate .eval_results into a single latest file per model
+  - Promote on social channels to drive initial adoption
+
+eval_metadata:
+  scanned_at: '2026-07-30T22:52:00+00:00'
+  source_endpoints:
+  - /api/models/Nanthasit/sakthai-plus-1.5b
+  - /api/models?author=Nanthasit&sort=downloads&direction=-1&limit=30
+  - /api/models/Nanthasit/sakthai-plus-1.5b/resolve/main/config.json
+  - HEAD direct resolve URLs for file sizes
+  previous_eval_files:
+  - sakthai-plus-1.5b-health.yaml (4016 bytes, earlier today)
+  - health-check-sakthai-plus-1.5b-2026-07-30.yaml (2416 bytes)
+  - health-check-sakthai-plus-1.5b-2026-07-30-2.yaml (2277 bytes)
+  - health-check-sakthai-plus-1.5b-2026-07-30-3.yaml (3365 bytes)
+  - health-check-sakthai-plus-1.5b-2026-07-31.yaml (4259 bytes)
--- a/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30.yaml
+++ b/.eval_results/health-check-sakthai-plus-1.5b-2026-07-30.yaml
@@ -0,0 +1,106 @@
+model: Nanthasit/sakthai-plus-1.5b
+eval_date: "2026-07-30T22:12:30.601577+00:00"
+
+metadata:
+  pipeline_tag: text-generation
+  library_name: transformers
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  license: apache-2.0
+  gated: false
+  private: false
+  created: "2026-07-30T13:02:40.000Z"
+  last_modified: "2026-07-30T22:06:30.000Z"
+  days_since_creation: 0
+  days_since_update: 0
+
+popularity:
+  downloads: 0
+  likes: 0
+  siblings_count: 19
+
+download_velocity:
+  total_downloads: 0
+  age_days: 0.38
+  downloads_per_day: 0.0
+  rank_among_siblings: New - insufficient data
+
+model_files:
+  - path: model.safetensors
+    size_bytes: 3087467144
+    size_display: "2.88 GB"
+    format: safetensors (BF16)
+
+total_repo_storage_bytes: 3098933908
+total_repo_storage_display: "2.89 GB"
+
+architecture:
+  model_type: qwen2
+  architecture: Qwen2ForCausalLM
+  context_length: 32768
+  hidden_size: 1536
+  num_layers: 28
+  num_attention_heads: 12
+  num_kv_heads: 2
+  intermediate_size: 8960
+  parameters: 1.54B
+  dtype: bfloat16
+  vocab_size: 151936
+
+benchmarks:
+  - benchmark: "SakThai Bench v2 (500 rows, scorer multiset-selection-v2)"
+    dataset: Nanthasit/sakthai-bench-v2
+    metrics:
+      Selection Accuracy: pending
+      Degenerate Rate: 0
+    verified: false
+
+tags:
+  - qwen2.5
+  - sakthai
+  - plus
+  - tool-calling
+  - conversational
+  - function-calling
+  - merged
+  - rslor
+  - house-of-sak
+  - family
+
+datasets:
+  - Nanthasit/sakthai-combined-v7
+  - Nanthasit/sakthai-combined-v8
+
+card_content:
+  readme_size_bytes: 6249
+  has_license: true
+  has_base_model: true
+  has_tags: true
+  has_datasets: true
+  has_widget: true
+
+health_score:
+  components:
+    popularity: 20
+    momentum: 20
+    benchmarks: 50
+    card_quality: 100
+    repo_hygiene: 85
+  adjustments:
+    - type: base_model_deduction
+      value: -20
+      reason: "Fine-tune of Qwen/Qwen2.5-1.5B-Instruct"
+    - type: pending_benchmarks
+      value: -10
+      reason: "Benchmark values are pending verification"
+  raw_score: 53.2
+  adjusted_score: 23.2
+
+assessment:
+  health: LOW
+  summary: "Model needs substantial improvement in adoption and benchmarks."
+  concerns:
+    - "Zero downloads - model is brand new, needs promotion"
+    - "Benchmark values are 'pending' - need to run verification"
+  recommendations:
+    - "Share model link in SakThai channels to drive initial adoption"
+    - "Run LightEval or HF Community Evals to fill in benchmark values"
--- a/.eval_results/inference-check-20260730T231504Z.yaml
+++ b/.eval_results/inference-check-20260730T231504Z.yaml
@@ -0,0 +1,26 @@
+check:
+  timestamp: 20260730T231504Z
+  model: Nanthasit/sakthai-plus-1.5b
+  method: HF Inference API (router.huggingface.co)
+  endpoint: https://router.huggingface.co/hf-inference/models/Nanthasit/sakthai-plus-1.5b
+results:
+  status: not_available
+  http_code: 400
+  response_time_seconds: 0.13
+  error: "Model not supported by provider hf-inference"
+  details: "The model is a Qwen2.5-1.5B based transformer (BF16 safetensors, 2.9GB) not deployed on any HF Inference provider. Serverless inference does not serve this model."
+alternative_attempts:
+  - method: "huggingface_hub InferenceClient.chat_completion"
+    status: "model_not_supported"
+    error: "The requested model 'Nanthasit/sakthai-plus-1.5b' is not supported by any provider you have enabled."
+  - method: "Local transformers (BF16, full precision)"
+    status: "OOM (exit 137)"
+    detail: "Environment has 7.8GB RAM total, 1.4GB available. Model requires ~3GB+ for weights."
+  - method: "Local transformers (4-bit quantization)"
+    status: "OOM (exit 137)"
+    detail: "Even 4-bit quantization failed due to insufficient memory."
+recommendations:
+  - "Convert model to GGUF format for llama.cpp inference (much lower memory footprint)"
+  - "Deploy on HF Inference Endpoints (requires paid GPU)"
+  - "Run on a machine with ≥8GB free RAM for CPU inference"
+  - "Enable the model for serverless inference via HF provider onboarding"
--- a/.eval_results/inference-check-20260730T234541Z.yaml
+++ b/.eval_results/inference-check-20260730T234541Z.yaml
@@ -0,0 +1,23 @@
+model: Nanthasit/sakthai-plus-1.5b
+check_type: inference-api
+timestamp: 20260730T234541Z
+status: unavailable
+endpoint_tried:
+  - endpoint: api-inference.huggingface.co
+    result: DNS resolution failed
+  - endpoint: router.huggingface.co/hf-inference
+    result: '400: model not supported by provider'
+  - endpoint: InferenceClient.text_generation
+    result: StopIteration - model not routable
+  - endpoint: InferenceClient.chat_completion
+    result: '400: model not supported by any enabled provider'
+details:
+  inference_field: null
+  inference_provider_mapping: null
+  model_type: qwen2
+  library: transformers
+  safetensors: true
+  params_bfloat16: 1543714304
+  reason: >
+    Model is not configured for HF Inference API serverless inference.
+    No Inference Endpoints deployed. Requires ~3GB RAM but only 1.4GB free.
--- a/.eval_results/inference-check-20260731T002943.yaml
+++ b/.eval_results/inference-check-20260731T002943.yaml
@@ -0,0 +1,51 @@
+eval_type: inference-check
+model: Nanthasit/sakthai-plus-1.5b
+timestamp: 2026-07-31T00:29:43Z
+results:
+  - method: curl POST to api-inference.huggingface.co
+    status: dns_unreachable
+    detail: "api-inference.huggingface.co does not resolve in sandbox DNS (gaierror -5)"
+    http_status: null
+    response_time_sec: null
+    output: null
+
+  - method: InferenceClient with provider='auto'
+    status: no_provider_mapping
+    detail: "Model has empty inference_provider_mapping; StopIteration in provider selection"
+    http_status: null
+    response_time_sec: 0.134
+    output: null
+
+  - method: InferenceClient with provider='hf-inference'
+    status: model_not_supported
+    detail: "BadRequestError: Model not supported by provider hf-inference"
+    http_status: 400
+    response_time_sec: 0.265
+    output: '{"error":"Model not supported by provider hf-inference"}'
+
+  - method: router.huggingface.co/v1/chat/completions
+    status: model_not_supported
+    detail: "Model not supported by any enabled provider"
+    http_status: 400
+    response_time_sec: 0.148
+    output: '{"error":{"message":"The requested model is not supported by any provider you have enabled.","code":"model_not_supported"}}'
+
+  - method: local transformers inference
+    status: oom
+    detail: "OOM (exit 137) — sandbox has 7.8GB RAM, 712MB free; 1.5B model requires ~3GB (fp16) or ~6GB (fp32)"
+    http_status: null
+    response_time_sec: null
+    output: null
+
+summary:
+  accessible: false
+  root_cause: |
+    The old inference API (api-inference.huggingface.co) is fully deprecated and has no DNS records.
+    The new Inference Providers router rejects the model because no provider has it in their catalog.
+    Local inference impossible due to memory constraints (712MB free).
+  recommendation: |
+    To get this model serving inference, either:
+    a) Enable serverless inference for the model on HF Hub (Settings → Inference), which makes
+       hf-inference provider load it on-demand.
+    b) Deploy a dedicated Inference Endpoint ($$ — not compatible with Zero-Cost First principle).
+    c) Convert to GGUF and run via llama.cpp on a machine with ≥4GB RAM.
--- 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: 39.7
+    name: Selection Accuracy
+    verified: true
+  - arguments: 61.7
+    name: Arguments Accuracy
+    verified: true
+  - strict: 39.7
+    name: Strict Accuracy
+    verified: true
--- a/.eval_results/sakthai-plus-1.5b-health.yaml
+++ b/.eval_results/sakthai-plus-1.5b-health.yaml
@@ -0,0 +1,140 @@
+task:
+  - text-generation
+  - model-health-check
+model: Nanthasit/sakthai-plus-1.5b
+timestamp: "2026-07-30T20:15:00Z"
+next_scheduled: "2026-07-31T20:15:00Z"
+
+model_info:
+  created_at: "2026-07-30T13:02:40.000Z"
+  last_modified: "2026-07-30T20:13:22.000Z"
+  pipeline_tag: text-generation
+  library_name: transformers
+  private: false
+  gated: false
+  license: apache-2.0
+  base_model: Qwen/Qwen2.5-1.5B-Instruct
+  tags:
+    - qwen2
+    - qwen2.5
+    - sakthai
+    - plus
+    - tool-calling
+    - function-calling
+    - merged
+    - rslor
+    - house-of-sak
+
+metrics:
+  downloads: 0
+  likes: 0
+  downloads_per_day: 0.0
+  days_since_last_update: 0.0
+  days_since_creation: 0.3
+  model_age_hours: 7.2
+
+config:
+  architecture: Qwen2ForCausalLM
+  dtype: bfloat16
+  hidden_size: 1536
+  intermediate_size: 8960
+  num_layers: 28
+  num_attention_heads: 12
+  num_key_value_heads: 2
+  max_position_embeddings: 32768
+  vocab_size: 151936
+  tie_word_embeddings: true
+  use_cache: true
+  transformers_version: "5.14.1"
+  generation_defaults:
+    temperature: 0.7
+    top_p: 0.8
+    top_k: 20
+    repetition_penalty: 1.1
+    do_sample: true
+
+files:
+  total_siblings: 11
+  total_repo_size_lfs_mb: 2944.4
+  model_weights:
+    - file: model.safetensors
+      lfs_size_bytes: 3087467144
+      lfs_size_mb: 2944.4
+      lfs_oid: "sha256:1d3e74e1a31c868d135a64f59963ce3292a790d7e46d2d7b0d1427e746d4d154"
+  config_files:
+    config.json: present
+    generation_config.json: present
+    tokenizer.json: present (LFS)
+    tokenizer_config.json: present
+    chat_template.jinja: present
+  eval_result_files:
+    - .eval_results/lighteval.yaml
+    - .eval_results/sakthai-bench-v2.yaml
+    - .eval_results/model-health-check.yaml
+
+checks:
+  - name: repo-exists
+    status: pass
+    detail: "Model repository Nanthasit/sakthai-plus-1.5b exists and is accessible"
+
+  - name: weights-uploaded
+    status: pass
+    detail: "model.safetensors present via LFS, 3087467144 bytes (2.88 GiB / 2.94 GB)"
+
+  - name: config-valid
+    status: pass
+    detail: "Qwen2-1.5B architecture: 28 layers, 12 heads, 2 KV heads, hidden=1536, inter=8960, vocab=151936, bf16, max_seq=32768, transformers 5.14.1"
+
+  - name: tokenizer-present
+    status: pass
+    detail: "tokenizer.json (LFS), tokenizer_config.json, and chat_template.jinja all present"
+
+  - name: model-card
+    status: pass
+    detail: "README.md (6249 bytes) with Apache-2.0 license, model-index, widget, tags, datasets, base_model references, and rich documentation"
+
+  - name: serverless-inference
+    status: fail
+    detail: "Model not supported by provider hf-inference (router returns HTTP 400). Standard api-inference endpoint unreachable (DNS failure). No free inference available for this model size at this time."
+
+  - name: eval-results
+    status: present
+    detail: "Three eval result files found in .eval_results/. sakthai-bench-v2: selection=84.8%, args=33.7%, strict=33.7%. lighteval: winogrande=59.6, gsm8k=50.9, hellaswag=34.0. All unverified."
+
+  - name: model-card-links
+    status: pass
+    detail: "Model linked to collection sakthai-model-family, datasets (v7, v8), and base model Qwen/Qwen2.5-1.5B-Instruct"
+
+  - name: download-traffic
+    status: cold
+    detail: "0 downloads, 0 likes. Model is <8 hours old — no organic traffic yet. Expected to grow as collection visibility increases."
+
+existing_benchmarks:
+  - name: lighteval
+    winogrande: 59.6
+    gsm8k: 50.9
+    hellaswag: 34.0
+    verified: false
+  - name: sakthai-bench-v2
+    selection_accuracy: 84.8
+    arguments_accuracy: 33.7
+    strict_accuracy: 33.7
+    verified: false
+  - name: model-health-check
+    status: current
+    checks_passed: 6
+    checks_failed: 1
+    checks_total: 9
+    note: "Only inference check fails — expected for a 2.9GB model without dedicated endpoint"
+
+health_score:
+  overall: "good"
+  score: 8.5
+  breakdown:
+    repo_integrity: 10
+    config_validity: 10
+    documentation: 10
+    inference_availability: 0
+    traffic_momentum: 0
+    benchmark_coverage: 8
+  max_score: 10
--- 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 +1,247 @@
+---
+language:
+- en
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- qwen2.5
+- sakthai
+- house-of-sak
+- tool-calling
+- function-calling
+- agent
+- instruct
+- finetuned
+- sft
+- merged
+- conversational
+- assistant
+- safetensors
+- cpu-inference
+- rsLoRA
+- benchmark
+- eval-results
+- llama-cpp
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+datasets:
+- Nanthasit/sakthai-combined-v11
+- Nanthasit/SimpleToolCalling
+inference:
+  parameters:
+    temperature: 0.3
+    max_new_tokens: 256
+    top_p: 0.9
+  widget:
+  - text: Send an email to Beer with the subject 'Status update' and body 'The model
+      is running well.'
+    output:
+      text: '<tool_call>{''name'': ''send_email'', ''arguments'': {''to'': ''Beer'',
+        ''subject'': ''Status update'', ''body'': ''The model is running well.''}}'
+  - text: What's the weather in Bangkok?
+    output:
+      text: '<tool_call>{''name'': ''get_weather'', ''arguments'': {''location'':
+        ''Bangkok''}}'
+extra:
+  downloads: 297
+  likes: 0
+  last_modified: 2026-08-01 07:31:41+00:00
+model-index:
+- name: sakthai-plus-1.5b
+  results:
+  - task:
+      type: text-generation
+      name: Tool-Calling Accuracy
+    dataset:
+      name: llama.cpp tool-calling (3-trial, q4_k_m)
+      type: custom
+    metrics:
+    - type: tool_call_success
+      value: 1.0
+      name: Tool Call Success Rate
+      verified: true
+    - type: valid-json
+      value: 1.0
+      name: Valid JSON Arguments
+      verified: true
+    - type: correct-answer
+      value: 1.0
+      name: Correct Answer Rate
+      verified: true
+    - type: selection-accuracy
+      value: 84.8
+      name: Selection Accuracy
+      verified: false
+    - type: arguments-accuracy
+      value: 33.7
+      name: Arguments Accuracy
+      verified: false
+    - type: strict-accuracy
+      value: 33.7
+      name: Strict Accuracy
+      verified: false
+  - task:
+      type: text-generation
+      name: Commonsense Reasoning
+    dataset:
+      name: lighteval
+      type: lighteval
+    metrics:
+    - type: winogrande
+      value: 59.6
+      name: WinoGrande (WSC)
+      verified: false
+    - type: hellaswag
+      value: 34.0
+      name: HellaSwag
+      verified: false
+    - type: gsm8k
+      value: 50.9
+      name: GSM8K
+      verified: false
+---
+## Benchmark Results
+
+**Benchmark:** [sakthai-bench-v2](https://huggingface.co/datasets/Nanthasit/sakthai-bench-v2) · 500 samples · run 2026-08-01
+
+**Overall (strict):** 39.65 · **Selection:** 39.65 · **Arguments:** 61.66
+
+| Category | Count | Selection | Arguments | Strict |
+|----------|-------|-----------|-----------|--------|
+| irrelevance_no_tools | 50 | 100.00 | 100.00 | 100.00 |
+| irrelevance_tools | 150 | 32.67 | 100.00 | 32.67 |
+| parallel | 137 | 43.80 | 43.80 | 43.80 |
+| simple | 122 | 18.85 | 18.85 | 18.85 |
+| held_out | - | 16.07 | 16.07 | 16.07 |
+
+
+## Training Data
+
+| Dataset | Rows | Description |
+|---------|------|-------------|
+| **Nanthasit/sakthai-combined-v11** | 2,003 | Multi-source tool-calling examples |
+| **Nanthasit/SimpleToolCalling** | 2,002 | Structured function-calling examples |
+
+## Benchmarks
+
+| Task | Metric | Score | Verified |
+|:-----|-------:|------:|:--------|
+| Tool Calling | Tool Call Success Rate | 1.0 | ✅ Yes |
+| Tool Calling | Valid JSON Arguments | 1.0 | ✅ Yes |
+| Tool Calling | Correct Answer Rate | 1.0 | ✅ Yes |
+| Tool Selection (v2) | Selection Accuracy | 84.8% | ❌ No |
+| Tool Selection (v2) | Strict Accuracy | 33.7% | ❌ No |
+| Commonsense | WinoGrande | 59.6% | ❌ No |
+| Commonsense | HellaSwag | 34.0% | ❌ No |
+| Math | GSM8K | 50.9% | ❌ No |
+
+## Quick Start
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Nanthasit/sakthai-plus-1.5b"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant with tool-calling capabilities."},
+    {"role": "user", "content": "What's the weather in Bangkok?"}
+]
+inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.3, do_sample=True)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Notes
+
+- 3/3 verified tool-calling score measured with llama.cpp q4_k_m.
+- Tool selection is strong, but argument accuracy needs refinement.
+- Unverified scores are single-trial; multi-trial replication is planned.
+- Trained on free T4 credits; no paid compute was used.
+
+## SakThai Family
+
+This README is part of the **SakThai Plus 1.5B** model card. The family links table is preserved to keep cross-repo navigation intact.
+
+| Repo | Downloads | Pipeline |
+|-----:|----------:|:---------|
+| [sakthai-plus-1.5b-lora](https://huggingface.co/Nanthasit/sakthai-plus-1.5b-lora) | 306 | text-generation |
+| [sakthai-context-1.5b-tools-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-tools-v2) | 192 | text-generation |
+| [sakthai-context-1.5b-merged-v2](https://huggingface.co/Nanthasit/sakthai-context-1.5b-merged-v2) | 354 | text-generation |
+
+Sibling rows are maintained for reference and kept in sync with live HF download counts during card audits.
+
+## Model Description
+
+SakThai Plus 1.5B is built for **agentic tool calling** rather than open-ended chat. It was trained on structured function-calling examples and merged from rsLoRA adapters into full weights. The model follows the Qwen2.5 chat format and emits function calls in JSON when a system prompt enables tools. It is optimized for small-footprint CPU and GPU inference, and works with both `transformers` and `llama.cpp`.
+
+Key traits:
+- Strong tool selection and reliable JSON argument formatting in verified tests.
+- Small 1.5B parameter size enables fast inference on CPUs and consumer GPUs.
+- Trained with zero paid compute on free-tier T4 credits.
+
+## How to Use
+
+### transformers chat template
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "Nanthasit/sakthai-plus-1.5b"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant with tool-calling capabilities. Use the available tools when asked."},
+    {"role": "user", "content": "Send an email to Beer with the subject 'Status update' and body 'The model is running well.'"}
+]
+
+inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.3, top_p=0.9)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### llama.cpp CLI
+
+This model also ships as GGUF in the SakThai family. Example inference with the GGUF build:
+
+```bash
+llama-cli -m sakthai-plus-1.5b.Q4_K_M.gguf \
+  -p "[INST] Send an email to Beer with the subject 'Status update' and body 'The model is running well.' [/INST]" \
+  --temp 0.3 -n 256 --top-p 0.9
+```
+
+## Benchmarks
+
+| Task | Metric | Score | Verified | Method |
+|-----|-------:|------:|:--------:|:-------|
+| Tool Calling | Tool Call Success Rate | 1.0 | ✅ Yes | llama.cpp q4_k_m, 3-trial |
+| Tool Calling | Valid JSON Arguments | 1.0 | ✅ Yes | llama.cpp q4_k_m, 3-trial |
+| Tool Calling | Correct Answer Rate | 1.0 | ✅ Yes | llama.cpp q4_k_m, 3-trial |
+| Tool Selection (v2) | Selection Accuracy | 84.8% | ❌ No | single-trial |
+| Tool Selection (v2) | Arguments Accuracy | 33.7% | ❌ No | single-trial |
+| Commonsense | WinoGrande | 59.6% | ❌ No | single-trial |
+| Commonsense | HellaSwag | 34.0% | ❌ No | single-trial |
+| Math | GSM8K | 50.9% | ❌ No | single-trial |
+
+Verified scores are reproducible across runs. Unverified rows should be treated as indicative until multi-trial replication is completed.
+
+## Limitations
+
+- Argument accuracy lags behind tool selection; complex nested parameters can still fail.
+- Unverified benchmarks are single-trial and may not reflect steady-state performance.
+- Strongest with short- to medium-length tool definitions; very large schemas may degrade accuracy.
+- Outputs should be parsed with a JSON-tolerant decoder because formatting can drift on low temperatures.
+
+## Citation
+
+```bibtex
+@misc{sakthai-plus-1.5b,
+  title  = {SakThai Plus 1.5B},
+  author = {Nanthasit},
+  year   = {2026},
+  url    = {https://huggingface.co/Nanthasit/sakthai-plus-1.5b}
+}
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}
--- 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": 21,
+  "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": true,
+  "transformers_version": "5.14.1",
+  "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": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.14.1"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f48574bfd3bb456da905112317f62319511ffdbb221a7ee07f87886fdd4c6d
+size 3087467144
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- 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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/vocab.json
+++ b/vocab.json