ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-10 16:21:23 +08:00
commit b479758669
13 changed files with 659636 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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

19
EVAL_RESULTS.md Normal file
View File

@@ -0,0 +1,19 @@
# External ToolACE Evaluation
- Base: `openbmb/MiniCPM5-1B`
- Adapter: `./minicpm5_tooluse_nemotron_dpo_from_repair_dpo`
- Eval dataset: `Team-ACE/ToolACE`
- Cases: `300`
| Metric | Base | Final adapter | Delta |
|---|---:|---:|---:|
| parseable_rate | 0.0133 | 0.9933 | +0.9800 |
| valid_name_rate | 0.0133 | 0.9700 | +0.9567 |
| expected_name_rate | 0.0133 | 0.9267 | +0.9133 |
| args_exact_rate | 0.1500 | 0.6533 | +0.5033 |
| arg_key_overlap | 0.0033 | 0.7517 | +0.7484 |
| no_schema_copy_rate | 1.0000 | 1.0000 | +0.0000 |
| no_repetition_rate | 0.9967 | 1.0000 | +0.0033 |
| stopped_cleanly_rate | 0.0000 | 0.1500 | +0.1500 |
Final adapter beats base on `7/8` metrics.

215
README.md Normal file
View File

@@ -0,0 +1,215 @@
---
license: apache-2.0
base_model: openbmb/MiniCPM5-1B
library_name: transformers
pipeline_tag: text-generation
model-index:
- name: MiniCPM5-1B Agentic Tooluse Merged FP16
results:
- task:
type: text-generation
name: Tool calling
dataset:
name: External ToolACE-derived first-call evaluation
type: Team-ACE/ToolACE
metrics:
- type: parseable_rate
value: 0.9933333333333333
name: Parseable tool-call rate
- type: valid_name_rate
value: 0.97
name: Available-tool name rate
- type: expected_name_rate
value: 0.9266666666666666
name: Expected tool-name rate
- type: args_exact_rate
value: 0.6533333333333333
name: Exact-arguments rate
tags:
- minicpm
- minicpm5
- minicpm5-1b
- tool-calling
- function-calling
- tool-use
- agentic
- xml-tool-calling
- transformers
- sglang
- vllm
- safetensors
- merged-model
- nemotron
- dpo
- openbmb
widget:
- text: "Use the available tool to create a note titled Team Meeting Agenda."
- text: "Run tests for the calculator bug using the available tool."
---
# MiniCPM5-1B Agentic Tooluse Merged FP16
Standalone merged FP16 checkpoint of
[`openbmb/MiniCPM5-1B`](https://huggingface.co/openbmb/MiniCPM5-1B)
and the latest
[`MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2`](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2)
adapter after the July 2026 Nemotron SFT+DPO repair.
This repository contains the complete model. It is **not** an adapter and does not require PEFT at inference time.
## Repositories
| Format | Repository |
|---|---|
| Merged FP16 Transformers model | This repository |
| LoRA/PEFT adapter | [`MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2`](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2) |
| F16, Q8_0 and Q4_K_M GGUF | [`MiniCPM5-1B-Agentic-Tooluse-GGUF`](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-GGUF) |
## Current Files
The current model weights are one indexed checkpoint:
- `model-00001-of-00002.safetensors`
- `model-00002-of-00002.safetensors`
- `model.safetensors.index.json`
The repository also includes the matching tokenizer, `chat_template.jinja`, model configuration, generation configuration and external evaluation artifacts. The previous single-file model remains recoverable from Hub history but is not part of the current branch.
## Tool-Calling Behavior
MiniCPM5-1B natively emits XML-style calls:
```xml
<function name="tool_name"><param name="parameter">value</param></function>
```
The fine-tuning specializes first-call tool selection, function-name accuracy, argument selection, schema-copy avoidance and repeated-call suppression.
An application remains responsible for parsing and validating calls, executing tools externally, and returning tool results in a new turn.
## Recommended Tool-Calling Deployment
OpenBMB recommends SGLang with its built-in MiniCPM5 parser:
```bash
pip install "sglang[srt]>=0.5.12"
python -m sglang.launch_server \
--model-path ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16 \
--port 30000 \
--tool-call-parser minicpm5
```
The parser converts a completed `<function ...>...</function>` block into an OpenAI-compatible `tool_calls` response.
## Transformers
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
dtype=torch.float16,
device_map="auto",
)
model.eval()
```
Use `tokenizer.apply_chat_template(...)` and the repository's matching chat template. For deterministic tool selection, override the sampling defaults:
```python
outputs = model.generate(
**inputs,
do_sample=False,
max_new_tokens=128,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
)
```
Remove `token_type_ids` from `inputs` if the installed Transformers/tokenizer combination returns them, because this Llama model does not consume that argument.
## vLLM
The merged safetensors checkpoint is the preferred format for vLLM:
```bash
vllm serve ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16
```
Parser availability depends on the installed vLLM release. Use SGLang's official `minicpm5` parser path when OpenAI-compatible tool-call extraction is required and the vLLM build does not provide an equivalent parser.
## External Evaluation
The final adapter and this merged checkpoint have identical weights for evaluation purposes. Evaluation used 300 examples derived from the external
[`Team-ACE/ToolACE`](https://huggingface.co/datasets/Team-ACE/ToolACE)
dataset, deterministic decoding, and the same cases for both models. This is not an official ToolACE or BFCL leaderboard submission.
| Metric | Base MiniCPM5-1B | Repaired model | Delta |
|---|---:|---:|---:|
| Parseable tool call | 0.0133 | 0.9933 | +0.9800 |
| Valid available-tool name | 0.0133 | 0.9700 | +0.9567 |
| Expected tool name | 0.0133 | 0.9267 | +0.9133 |
| Exact arguments | 0.1500 | 0.6533 | +0.5033 |
| Argument-key overlap | 0.0033 | 0.7517 | +0.7484 |
| No schema copying | 1.0000 | 1.0000 | +0.0000 |
| No repetition | 0.9967 | 1.0000 | +0.0033 |
| Natural clean termination | 0.0000 | 0.1500 | +0.1500 |
The full rows and metrics are published in:
- `external_toolace_base_vs_nemotron_dpo_eval.json`
- `EVAL_RESULTS.md`
## Understanding the 15% Termination Metric
`stopped_cleanly_rate=0.15` is a strict natural-termination metric. It measures whether the model naturally ended immediately after a completed function call without runtime intervention.
It does **not** mean that only 15% of cases produced usable calls. In the same evaluation, 99.33% were parseable, 97% used an available tool name, and 92.67% selected the expected tool.
MiniCPM5's deployment contract uses a parser to extract the completed XML function block. Production should treat the first completed `</function>` as the action boundary and prevent generated synthetic tool responses or later dialogue from being interpreted as additional actions.
## Training Lineage
The current adapter was produced by:
1. Earlier xLAM/Glaive SFT and preference-repair stages.
2. Targeted Nemotron SFT continuation from the previous DPO adapter.
3. DPO preference optimization over valid versus corrupted tool calls.
4. Merge into `openbmb/MiniCPM5-1B`.
Nemotron sources used in the repair:
- `nvidia/Nemotron-SFT-Agentic-v2`
- `nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1`
- `nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1`
The data pipeline inspected physical dataset files, skipped one malformed JSONL row in the SFT tool-calling file, removed oversized policy text where needed, preserved tool schemas and recent context, and rejected unknown arguments, schema-copy placeholders and invalid expected tools.
## Measured Improvements and Scope
This merged checkpoint contains the same repaired adapter behavior and improved every reported task-quality metric over base MiniCPM5-1B:
- Parseable calls: **1.33% -> 99.33%**
- Valid available-tool names: **1.33% -> 97.00%**
- Expected-tool selection: **1.33% -> 92.67%**
- Exact arguments: **15.00% -> 65.33%**
- Argument-key overlap: **0.33% -> 75.17%**
- No repetition: **99.67% -> 100.00%**
- Natural clean termination: **0.00% -> 15.00%**
The remaining gap to 100% is residual error after a large improvement, not evidence that merging or fine-tuning degraded the base model.
## Deployment Notes
- Schema validation, permission checks and confirmation for sensitive actions are standard requirements for every tool-calling model.
- Exact-argument accuracy improved by **50.33 percentage points**; applications should still validate generated values before execution.
- Valid-name accuracy improved by **95.67 percentage points**; rare near misses can remain on unseen tool libraries.
- Natural termination improved from 0% to 15%. MiniCPM5's parser-based serving contract extracts the completed call, so this metric is separate from the 99.33% parseable-call rate.
- The external evaluation is custom rather than an official ToolACE/BFCL leaderboard submission.
- GGUF quantizations may differ slightly from FP16 and are published separately.

179
chat_template.jinja Normal file
View File

@@ -0,0 +1,179 @@
{{- bos_token }}{%- if tools %}
{%- set tool_definitions %}
{{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson(ensure_ascii=False) }}
{%- endfor %}
{{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
{%- endset %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{%- if '<tool_def_sep>' in messages[0].content %}
{{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
{%- else %}
{{- messages[0].content + '\n\n' + tool_definitions }}
{%- endif %}
{%- else %}
{{- tool_definitions.lstrip() }}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if message.tool_calls %}
{%- set content_parts = content.split('<tool_sep>') %}
{%- set processed_content = content_parts[0] %}
{%- set tool_calls_count = message.tool_calls|length %}
{%- set tool_sep_count = content_parts|length - 1 %}
{%- set min_count = [tool_calls_count, tool_sep_count]|min %}
{%- for i in range(1, content_parts|length) %}
{%- set tool_index = i - 1 %}
{%- if tool_index < tool_calls_count %}
{%- set tool_call = message.tool_calls[tool_index] %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- set single_tool_xml %}
{{- '<function name="' ~ tool_call.name ~ '">' }}
{%- if tool_call.arguments %}
{%- set args_dict = tool_call.arguments %}
{%- for param_name, param_value in args_dict.items() %}
{{- '<param name="' ~ param_name ~ '">' }}
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
{{- '<![CDATA[' + param_value + ']]>' }}
{%- else %}
{{- param_value }}
{%- endif %}
{{- '</param>' }}
{%- endfor %}
{%- endif %}
{{- '</function>' }}
{%- endset %}
{%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
{%- else %}
{%- set processed_content = processed_content + content_parts[i] %}
{%- endif %}
{%- endfor %}
{%- if tool_calls_count > tool_sep_count %}
{%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
{%- set tool_call = message.tool_calls[remaining_index] %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- set remaining_tool_xml %}
{{- '<function name="' ~ tool_call.name ~ '">' }}
{%- if tool_call.arguments %}
{%- set args_dict = tool_call.arguments %}
{%- for param_name, param_value in args_dict.items() %}
{{- '<param name="' ~ param_name ~ '">' }}
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
{{- '<![CDATA[' + param_value + ']]>' }}
{%- else %}
{{- param_value }}
{%- endif %}
{{- '</param>' }}
{%- endfor %}
{%- endif %}
{{- '</function>' }}
{%- endset %}
{%- set processed_content = processed_content + remaining_tool_xml %}
{%- endfor %}
{%- endif %}
{%- set content = processed_content %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if reasoning_content %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls and not has_tool_sep %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<function name="' ~ tool_call.name ~ '">' }}
{%- if tool_call.arguments %}
{%- set args_dict = tool_call.arguments %}
{%- for param_name, param_value in args_dict.items() %}
{{- '<param name="' ~ param_name ~ '">' }}
{%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
{{- '<![CDATA[' + param_value + ']]>' }}
{%- else %}
{{- param_value }}
{%- endif %}
{{- '</param>' }}
{%- endfor %}
{%- endif %}
{{- '</function>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{%- if message.content is string %}
{{- content }}
{%- else %}
{{- message.content | tojson(ensure_ascii=False) }}
{%- endif %}
{{- '\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' }}
{%- if enable_thinking is defined %}
{%- if enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- elif enable_thinking is true %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}
{%- endif %}

33
config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "float16",
"eos_token_id": [
1,
130073
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 4608,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 1,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 5000000,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": true,
"vocab_size": 130560
}

836
external_toolace_base_vs_nemotron_dpo_eval.json Normal file
View File

@@ -0,0 +1,836 @@
{
"base_model_id": "openbmb/MiniCPM5-1B",
"final_adapter_dir": "./minicpm5_tooluse_nemotron_dpo_from_repair_dpo",
"hf_repo_id": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2",
"eval_dataset_id": "Team-ACE/ToolACE",
"base_metrics": {
"n": 300,
"parseable_rate": 0.013333333333333334,
"valid_name_rate": 0.013333333333333334,
"expected_name_rate": 0.013333333333333334,
"args_exact_rate": 0.15,
"no_schema_copy_rate": 1.0,
"no_repetition_rate": 0.9966666666666667,
"stopped_cleanly_rate": 0.0,
"arg_key_overlap": 0.0033333333333333335,
"seconds": 344.0649447441101,
"cases_per_second": 0.871928409397004
},
"final_metrics": {
"n": 300,
"parseable_rate": 0.9933333333333333,
"valid_name_rate": 0.97,
"expected_name_rate": 0.9266666666666666,
"args_exact_rate": 0.6533333333333333,
"no_schema_copy_rate": 1.0,
"no_repetition_rate": 1.0,
"stopped_cleanly_rate": 0.15,
"arg_key_overlap": 0.7517222222222223,
"seconds": 284.4572868347168,
"cases_per_second": 1.054639884034028
},
"base_bad_rows": [
{
"i": 0,
"label": "base",
"expected": "Market Trends API",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to know the top market trends in the US. Let me check the available tools. There's a Market Trends API that requires country (2-letter code), language (2-letter code), and trend type. The user specified US, so country should be us. The language is en by default. The trend type needs to be one of the enum values: MARKET_INDEXES, MOST_ACTIVE, GAINERS, LOSERS, CRYPT",
"first_call": "<think>\nOkay, the user wants to know the top market trends in the US. Let me check the available tools. There's a Market Trends API that requires country (2-letter code), language (2-letter code), and trend type. The user specified US, so country should be us. The language is en by default. The trend type needs to be one of the enum values: MARKET_INDEXES, MOST_ACTIVE, GAINERS, LOSERS, CRYPT"
},
{
"i": 1,
"label": "base",
"expected": "Quotes by Keywords",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for quotes about \"inspiration\". Let me check the available tools.\n\nLooking at the tools list, there's one called \"Quotes by Keywords\" that takes a \"word\" parameter. The required parameter is \"word\", which is \"inspiration\". So I need to call that function with the word \"inspiration\".\n\nI should make sure I'm using the correct tool. The other tools are for zip codes",
"first_call": "<think>\nOkay, the user is asking for quotes about \"inspiration\". Let me check the available tools.\n\nLooking at the tools list, there's one called \"Quotes by Keywords\" that takes a \"word\" parameter. The required parameter is \"word\", which is \"inspiration\". So I need to call that function with the word \"inspiration\".\n\nI should make sure I'm using the correct tool. The other tools are for zip codes"
},
{
"i": 2,
"label": "base",
"expected": "GetCompetitions",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the list of football competitions that are currently televised in Peru. Let me check the available tools to see which one can do that.\n\nLooking at the tools provided, there's one called \"GetCompetitions\" which says it retrieves a list of football competitions that are televised in Peru. The parameters require an empty list, so I don't need any parameters. The other tools are for manager images, search competitions, and category",
"first_call": "<think>\nOkay, the user is asking for the list of football competitions that are currently televised in Peru. Let me check the available tools to see which one can do that.\n\nLooking at the tools provided, there's one called \"GetCompetitions\" which says it retrieves a list of football competitions that are televised in Peru. The parameters require an empty list, so I don't need any parameters. The other tools are for manager images, search competitions, and category"
},
{
"i": 3,
"label": "base",
"expected": "GetFutureEvents",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for a list of upcoming Azure events, starting with the first page. Let me check the available tools.\n\nLooking at the tools, there's one called \"GetFutureEvents\" which is for that purpose. The parameters require a page number, defaulting to 1. The user specified to start with the first page, so I should use page=1.\n\nI need to make sure I call that function with page=1.",
"first_call": "<think>\nOkay, the user is asking for a list of upcoming Azure events, starting with the first page. Let me check the available tools.\n\nLooking at the tools, there's one called \"GetFutureEvents\" which is for that purpose. The parameters require a page number, defaulting to 1. The user specified to start with the first page, so I should use page=1.\n\nI need to make sure I call that function with page=1."
},
{
"i": 4,
"label": "base",
"expected": "/madlibs-diceware",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants a unique and memorable password for a new account using two phrases. Let me check the available tools.\n\nLooking at the tools, there's a function called \"generate_password\" which uses madlibs diceware. The parameters require nphrase (between 1 and 2). The user specified two phrases, so I need to set nphrase=2.\n\nWait, the tool's description says \"nphrase\" is an integer between",
"first_call": "<think>\nOkay, the user wants a unique and memorable password for a new account using two phrases. Let me check the available tools.\n\nLooking at the tools, there's a function called \"generate_password\" which uses madlibs diceware. The parameters require nphrase (between 1 and 2). The user specified two phrases, so I need to set nphrase=2.\n\nWait, the tool's description says \"nphrase\" is an integer between"
},
{
"i": 5,
"label": "base",
"expected": "Trending Videos",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the latest trending videos on YouTube. Let me check the available tools.\n\nLooking at the tools list, there's one called \"Trending Videos\" that takes parameters like gl (country, default US), hl (locale), and type (default mu). The user didn't specify any parameters, so I should call this function with the default values.\n\nWait, the parameters for the tool have a default for gl as \"US",
"first_call": "<think>\nOkay, the user is asking for the latest trending videos on YouTube. Let me check the available tools.\n\nLooking at the tools list, there's one called \"Trending Videos\" that takes parameters like gl (country, default US), hl (locale), and type (default mu). The user didn't specify any parameters, so I should call this function with the default values.\n\nWait, the parameters for the tool have a default for gl as \"US"
},
{
"i": 6,
"label": "base",
"expected": "Get Baseball Schedule",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, let's see. The user wants to get the schedule for a baseball game on January 15th, 2024. I need to check which tool to use.\n\nLooking at the available tools, there's one called \"Get Baseball Schedule\" that takes a string in YYYY-MM-DD format. The required parameter is \"string\", which matches the user's request. The other tools are for football rankings, pitching leaders, and top sports data",
"first_call": "<think>\nOkay, let's see. The user wants to get the schedule for a baseball game on January 15th, 2024. I need to check which tool to use.\n\nLooking at the available tools, there's one called \"Get Baseball Schedule\" that takes a string in YYYY-MM-DD format. The required parameter is \"string\", which matches the user's request. The other tools are for football rankings, pitching leaders, and top sports data"
},
{
"i": 7,
"label": "base",
"expected": "Get Suggestion",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is planning a trip to Japan and wants to know popular games to help them understand local culture. Let me check the available tools.\n\nLooking at the tools, there's a function called \"Get Suggestion\" that returns game suggestions based on the term, language, and country. The parameters required are term, language, and country. The user mentioned Japan, so I need to set country to \"Japan\" and language to \"en\" (assuming",
"first_call": "<think>\nOkay, the user is planning a trip to Japan and wants to know popular games to help them understand local culture. Let me check the available tools.\n\nLooking at the tools, there's a function called \"Get Suggestion\" that returns game suggestions based on the term, language, and country. The parameters required are term, language, and country. The user mentioned Japan, so I need to set country to \"Japan\" and language to \"en\" (assuming"
},
{
"i": 8,
"label": "base",
"expected": "Text Analysis",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, let's see. The user wants to analyze the sentiment of customer feedback. They provided the text: \"The service was excellent, but the wait time was too long. I might not come back because of that.\"\n\nFirst, I need to check which tool to use. The available tools are Text Analysis, Terminology Extraction API, Token Splitter, and Correct Sentence. The user is asking for sentiment analysis, so the first tool should be the right choice.",
"first_call": "<think>\nOkay, let's see. The user wants to analyze the sentiment of customer feedback. They provided the text: \"The service was excellent, but the wait time was too long. I might not come back because of that.\"\n\nFirst, I need to check which tool to use. The available tools are Text Analysis, Terminology Extraction API, Token Splitter, and Correct Sentence. The user is asking for sentiment analysis, so the first tool should be the right choice."
},
{
"i": 9,
"label": "base",
"expected": "Hashtag Info API",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to get details about the hashtag #funnychallenge on TikTok. Let me check the available tools. There's a function called Hashtag Info API that requires the hashtag. The parameters need the hashtag as a string. The user provided #funnychallenge, so I should call that function with that hashtag. I need to make sure the parameters are correctly formatted. The hashtag is required, so I'll structure",
"first_call": "<think>\nOkay, the user wants to get details about the hashtag #funnychallenge on TikTok. Let me check the available tools. There's a function called Hashtag Info API that requires the hashtag. The parameters need the hashtag as a string. The user provided #funnychallenge, so I should call that function with that hashtag. I need to make sure the parameters are correctly formatted. The hashtag is required, so I'll structure"
},
{
"i": 10,
"label": "base",
"expected": "Get Web Pair Details",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the current trading details for the pair ETH-USDC on SushiSwap. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Get Web Pair Details\" which requires chain_slug, exchange_slug, and pair_slug. The user mentioned SushiSwap, so I need to set exchange_slug to \"sushiswap\". The pair_s",
"first_call": "<think>\nOkay, the user is asking for the current trading details for the pair ETH-USDC on SushiSwap. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Get Web Pair Details\" which requires chain_slug, exchange_slug, and pair_slug. The user mentioned SushiSwap, so I need to set exchange_slug to \"sushiswap\". The pair_s"
},
{
"i": 11,
"label": "base",
"expected": "Get Trending News",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants the latest financial news related to stocks from the last day. Let me check the available tools.\n\nLooking at the tools, there's \"Get Trending News\" which requires category and timeframe. The category should be \"Stocks\" as per the user's request. The timeframe needs to be \"1 day\" for the last day.\n\nWait, the parameters for Get Trending News have category as a string and timeframe as",
"first_call": "<think>\nOkay, the user wants the latest financial news related to stocks from the last day. Let me check the available tools.\n\nLooking at the tools, there's \"Get Trending News\" which requires category and timeframe. The category should be \"Stocks\" as per the user's request. The timeframe needs to be \"1 day\" for the last day.\n\nWait, the parameters for Get Trending News have category as a string and timeframe as"
},
{
"i": 12,
"label": "base",
"expected": "get_regions",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking if I can find out where they can download TikTok videos for different regions. Let me check the available tools to see if any can help with that.\n\nLooking at the tools provided: there's get_regions, which is for retrieving regions supported by the TikTok download video tool. The description says it's for a list of regions, but the parameters are empty. Wait, the parameters are null, so maybe it's a function",
"first_call": "<think>\nOkay, the user is asking if I can find out where they can download TikTok videos for different regions. Let me check the available tools to see if any can help with that.\n\nLooking at the tools provided: there's get_regions, which is for retrieving regions supported by the TikTok download video tool. The description says it's for a list of regions, but the parameters are empty. Wait, the parameters are null, so maybe it's a function"
},
{
"i": 13,
"label": "base",
"expected": "S_YTD",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to download a video from YouTube. Let me check the available tools.\n\nLooking at the tools list, there's one called S_YTD which downloads videos from a specified source. The parameters needed are output_path and video_url. The output_path is the path where the video will be saved, and video_url is the source URL.\n\nThe user provided the video URL: https://www.youtube.com/watch?v=dQw4w9Wg",
"first_call": "<think>\nOkay, the user wants to download a video from YouTube. Let me check the available tools.\n\nLooking at the tools list, there's one called S_YTD which downloads videos from a specified source. The parameters needed are output_path and video_url. The output_path is the path where the video will be saved, and video_url is the source URL.\n\nThe user provided the video URL: https://www.youtube.com/watch?v=dQw4w9Wg"
},
{
"i": 14,
"label": "base",
"expected": "Get Current Time by IP",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the current time for the IP address 192.168.1.1. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Get Current Time by IP\" which requires the ipv4 parameter. The required parameter is ipv4, which is a string. The user provided 192.168.1.1, so I need to call that function with that IP.",
"first_call": "<think>\nOkay, the user is asking for the current time for the IP address 192.168.1.1. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Get Current Time by IP\" which requires the ipv4 parameter. The required parameter is ipv4, which is a string. The user provided 192.168.1.1, so I need to call that function with that IP."
},
{
"i": 15,
"label": "base",
"expected": "Financial Fundamentals API",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the ROA (Return on Assets) ratio for a specific share with shareuid 6789 for the last financial year. Let me check the available tools.\n\nLooking at the tools provided, there's a Financial Fundamentals API that requires shareuid, from, and to parameters. The required parameters are shareuid, from, and to. The user mentioned \"last financial year,\" so I need to determine the correct year. The from",
"first_call": "<think>\nOkay, the user is asking for the ROA (Return on Assets) ratio for a specific share with shareuid 6789 for the last financial year. Let me check the available tools.\n\nLooking at the tools provided, there's a Financial Fundamentals API that requires shareuid, from, and to parameters. The required parameters are shareuid, from, and to. The user mentioned \"last financial year,\" so I need to determine the correct year. The from"
},
{
"i": 16,
"label": "base",
"expected": "Daily 4 History API",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to fetch the past month's Daily 4 lottery results from May 20th to today. Let me check the available tools.\n\nFirst, I need to use the Daily 4 History API. The parameters required are start_string and end_string, both in YYYY-MM-DD format. The user specified May 20th, so I need to convert that to the correct format. May is the 5th month, so",
"first_call": "<think>\nOkay, the user wants to fetch the past month's Daily 4 lottery results from May 20th to today. Let me check the available tools.\n\nFirst, I need to use the Daily 4 History API. The parameters required are start_string and end_string, both in YYYY-MM-DD format. The user specified May 20th, so I need to convert that to the correct format. May is the 5th month, so"
},
{
"i": 17,
"label": "base",
"expected": "Get All Tags",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants a list of all tags in the system. Let me check the available tools. There's a function called GetAllTags that returns a list of tags ordered alphabetically. The parameters require an empty dict, so I don't need any arguments. I should call that function.\n\nWait, the user is asking for the list of tags, so I need to make sure I'm using the correct tool. The other tools are for videos, files,",
"first_call": "<think>\nOkay, the user wants a list of all tags in the system. Let me check the available tools. There's a function called GetAllTags that returns a list of tags ordered alphabetically. The parameters require an empty dict, so I don't need any arguments. I should call that function.\n\nWait, the user is asking for the list of tags, so I need to make sure I'm using the correct tool. The other tools are for videos, files,"
},
{
"i": 18,
"label": "base",
"expected": "/email/valistring",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to check if \"suspicious@example.com\" is authentic. Let me check the available tools.\n\nLooking at the tools provided, there's one called valistring which checks email validity and authenticity. The parameters needed are \"email\" and it's required. The description says it checks against various criteria.\n\nSo I need to call that tool with the email \"suspicious@example.com\". The other tools are for retrieving emails, exporting",
"first_call": "<think>\nOkay, the user wants to check if \"suspicious@example.com\" is authentic. Let me check the available tools.\n\nLooking at the tools provided, there's one called valistring which checks email validity and authenticity. The parameters needed are \"email\" and it's required. The description says it checks against various criteria.\n\nSo I need to call that tool with the email \"suspicious@example.com\". The other tools are for retrieving emails, exporting"
},
{
"i": 19,
"label": "base",
"expected": "Page Info",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to fetch insights about the Facebook page for \"Green Earth Grocery\" at the provided URL. Let me check the available tools.\n\nLooking at the tools list, there's a function called \"Page Info\" which requires the URL. The parameters need the URL as a string. The user provided the URL as https://www.facebook.com/GreenEarthGrocery, so I should call that function with that URL.\n\nI need to make sure",
"first_call": "<think>\nOkay, the user wants to fetch insights about the Facebook page for \"Green Earth Grocery\" at the provided URL. Let me check the available tools.\n\nLooking at the tools list, there's a function called \"Page Info\" which requires the URL. The parameters need the URL as a string. The user provided the URL as https://www.facebook.com/GreenEarthGrocery, so I should call that function with that URL.\n\nI need to make sure"
},
{
"i": 20,
"label": "base",
"expected": "GetFutureEventsByTopic",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user wants to find upcoming AI-related events on page 1. Let me check the available tools.\n\nLooking at the first tool: \"GetFutureEventsByTopic\" requires topic and page. The parameters need topic and page. The user specified \"artificial intelligence\" as the topic, but the tool's description says \"topic\" is a string, so maybe the topic should be \"artificial intelligence\" as a string. The page is 1, so",
"first_call": "<think>\nOkay, the user wants to find upcoming AI-related events on page 1. Let me check the available tools.\n\nLooking at the first tool: \"GetFutureEventsByTopic\" requires topic and page. The parameters need topic and page. The user specified \"artificial intelligence\" as the topic, but the tool's description says \"topic\" is a string, so maybe the topic should be \"artificial intelligence\" as a string. The page is 1, so"
},
{
"i": 21,
"label": "base",
"expected": "GetDividendHistory",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the recent dividend history for AAPL. Let me check the available tools.\n\nLooking at the tools list, there's a function called GetDividendHistory that requires the symbol. The parameters need the symbol and orderBy. The user specified \"recent\", so I should set orderBy to \"Descending\" as per the default but the parameter allows \"Ascending\" or \"Descending\", so I'll use \"Descending\".",
"first_call": "<think>\nOkay, the user is asking for the recent dividend history for AAPL. Let me check the available tools.\n\nLooking at the tools list, there's a function called GetDividendHistory that requires the symbol. The parameters need the symbol and orderBy. The user specified \"recent\", so I should set orderBy to \"Descending\" as per the default but the parameter allows \"Ascending\" or \"Descending\", so I'll use \"Descending\"."
},
{
"i": 22,
"label": "base",
"expected": "Top NFT Sales Today",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the top 5 NFT sales for today. Let me check the available tools.\n\nLooking at the tools provided, there's one called \"Top NFT Sales Today\" which requires limit, marketplace, and offset. The user didn't specify a marketplace, so I need to assume it's defaulting to the main one, probably OpenSea.\n\nWait, the parameters need limit, which is required. The user wants 5",
"first_call": "<think>\nOkay, the user is asking for the top 5 NFT sales for today. Let me check the available tools.\n\nLooking at the tools provided, there's one called \"Top NFT Sales Today\" which requires limit, marketplace, and offset. The user didn't specify a marketplace, so I need to assume it's defaulting to the main one, probably OpenSea.\n\nWait, the parameters need limit, which is required. The user wants 5"
},
{
"i": 23,
"label": "base",
"expected": "Hashtag Feed V2",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the latest Instagram posts for the hashtag #Halloween2026. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Hashtag Feed V2\" that retrieves posts based on a hashtag. The required parameter is hashtag, which is a string. The other tool is for Twitter images, and the second one is for Pinterest pins. \n\nThe user specifically wants",
"first_call": "<think>\nOkay, the user is asking for the latest Instagram posts for the hashtag #Halloween2026. Let me check the available tools.\n\nLooking at the tools provided, there's a function called \"Hashtag Feed V2\" that retrieves posts based on a hashtag. The required parameter is hashtag, which is a string. The other tool is for Twitter images, and the second one is for Pinterest pins. \n\nThe user specifically wants"
},
{
"i": 24,
"label": "base",
"expected": "Season Kills Leaderboard MW 2",
"pred": "",
"parseable": false,
"valid_name": false,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<think>\nOkay, the user is asking for the top players' statistics for the current season in Modern Warfare 2, including their kill counts. Let me check the available tools.\n\nLooking at the tools provided, there's one called \"Season Kills Leaderboard MW 2\" which requires a season parameter. The parameters need a season (string) and a limit (default 2000). The user didn't specify a season, so I need to ask for that.",
"first_call": "<think>\nOkay, the user is asking for the top players' statistics for the current season in Modern Warfare 2, including their kill counts. Let me check the available tools.\n\nLooking at the tools provided, there's one called \"Season Kills Leaderboard MW 2\" which requires a season parameter. The parameters need a season (string) and a limit (default 2000). The user didn't specify a season, so I need to ask for that."
}
],
"final_bad_rows": [
{
"i": 0,
"label": "final",
"expected": "Market Trends API",
"pred": "Market Trends API",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Market Trends API\"><param name=\"trend_type\">MOST_ACTIVE</param><param name=\"country\">US</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Market Trends API\"><param name=\"trend_type\">MOST_ACTIVE</param><param name=\"country\">US</param></function>"
},
{
"i": 1,
"label": "final",
"expected": "Quotes by Keywords",
"pred": "Quotes by Keywords",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Quotes by Keywords\"><param name=\"word\">inspiration</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Quotes by Keywords\"><param name=\"word\">inspiration</param></function>"
},
{
"i": 2,
"label": "final",
"expected": "GetCompetitions",
"pred": "GetCompetitions",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetCompetitions\"></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"GetCompetitions\"></function>"
},
{
"i": 3,
"label": "final",
"expected": "GetFutureEvents",
"pred": "GetFutureEvents",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetFutureEvents\"><param name=\"page\">1</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"GetFutureEvents\"><param name=\"page\">1</param></function>"
},
{
"i": 4,
"label": "final",
"expected": "/madlibs-diceware",
"pred": "Get Synthesize",
"parseable": true,
"valid_name": true,
"expected_name": false,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get Synthesize\"><param name=\"text\">My new account is a place where I can explore and share ideas with others. It's a place where I can share my thoughts, ideas, and experiences with others. It's a place where I can learn, grow, and evolve. It's a place where I can connect with others and make a positive impact. It's a place where I can grow and learn. It's a place where I can share",
"first_call": "<function name=\"Get Synthesize\"><param name=\"text\">My new account is a place where I can explore and share ideas with others. It's a place where I can share my thoughts, ideas, and experiences with others. It's a place where I can learn, grow, and evolve. It's a place where I can connect with others and make a positive impact. It's a place where I can grow and learn. It's a place where I can share"
},
{
"i": 5,
"label": "final",
"expected": "Trending Videos",
"pred": "Trending Videos",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Trending Videos\"><param name=\"gl\">US</param><param name=\"hl\">en</param><param name=\"type\">mu</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Trending Videos\"><param name=\"gl\">US</param><param name=\"hl\">en</param><param name=\"type\">mu</param></function>"
},
{
"i": 6,
"label": "final",
"expected": "Get Baseball Schedule",
"pred": "Get Baseball Schedule",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get Baseball Schedule\"><param name=\"string\">2024-01-15</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Get Baseball Schedule\"><param name=\"string\">2024-01-15</param></function>"
},
{
"i": 7,
"label": "final",
"expected": "Get Suggestion",
"pred": "Get Suggestion",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get Suggestion\"><param name=\"country\">Japan</param><param name=\"lang\">en</param><param name=\"term\">japanese</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Get Suggestion\"><param name=\"country\">Japan</param><param name=\"lang\">en</param><param name=\"term\">japanese</param></function>"
},
{
"i": 8,
"label": "final",
"expected": "Text Analysis",
"pred": "Text Analysis",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Text Analysis\"><param name=\"text\">The service was excellent, but the wait time was too long. I might not come back because of that.</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Text Analysis\"><param name=\"text\">The service was excellent, but the wait time was too long. I might not come back because of that.</param></function>"
},
{
"i": 9,
"label": "final",
"expected": "Hashtag Info API",
"pred": "Hashtag Info API",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Hashtag Info API\"><param name=\"hashtag\">#funnychallenge</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Hashtag Info API\"><param name=\"hashtag\">#funnychallenge</param></function>"
},
{
"i": 11,
"label": "final",
"expected": "Get Trending News",
"pred": "Get Trending News",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get Trending News\"><param name=\"category\">Stocks</param><param name=\"timeframe\">1 day</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Get Trending News\"><param name=\"category\">Stocks</param><param name=\"timeframe\">1 day</param></function>"
},
{
"i": 12,
"label": "final",
"expected": "get_regions",
"pred": "get_regions",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"get_regions\"></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"get_regions\"></function>"
},
{
"i": 13,
"label": "final",
"expected": "S_YTD",
"pred": "S_YTD",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"S_YTD\"><param name=\"output_path\">desktop</param><param name=\"video_url\">https://www.youtube.com/watch?v=dQw4w9WgXcQ</param></function><|im_end|>\n</s></s></s></s></s>",
"first_call": "<function name=\"S_YTD\"><param name=\"output_path\">desktop</param><param name=\"video_url\">https://www.youtube.com/watch?v=dQw4w9WgXcQ</param></function>"
},
{
"i": 14,
"label": "final",
"expected": "Get Current Time by IP",
"pred": "Get Current Time by IP",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get Current Time by IP\"><param name=\"ipv4\">192.168.1.1</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Get Current Time by IP\"><param name=\"ipv4\">192.168.1.1</param></function>"
},
{
"i": 15,
"label": "final",
"expected": "Financial Fundamentals API",
"pred": "Financial Fundamentals API",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Financial Fundamentals API\"><param name=\"from\">2022-01-01</param><param name=\"shareuid\">6789</param><param name=\"to\">2022-12-31</param></function><|im_end|>\n</s></s></s></s>",
"first_call": "<function name=\"Financial Fundamentals API\"><param name=\"from\">2022-01-01</param><param name=\"shareuid\">6789</param><param name=\"to\">2022-12-31</param></function>"
},
{
"i": 17,
"label": "final",
"expected": "Get All Tags",
"pred": "Get All Tags",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Get All Tags\"></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Get All Tags\"></function>"
},
{
"i": 18,
"label": "final",
"expected": "/email/valistring",
"pred": "GetEmailMessages",
"parseable": true,
"valid_name": false,
"expected_name": false,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetEmailMessages\"><param name=\"email\">suspicious@example.com</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"GetEmailMessages\"><param name=\"email\">suspicious@example.com</param></function>"
},
{
"i": 19,
"label": "final",
"expected": "Page Info",
"pred": "Page Info",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Page Info\"><param name=\"url\">https://www.facebook.com/GreenEarthGrocery</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Page Info\"><param name=\"url\">https://www.facebook.com/GreenEarthGrocery</param></function>"
},
{
"i": 20,
"label": "final",
"expected": "GetFutureEventsByTopic",
"pred": "GetFutureEventsByTopic",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetFutureEventsByTopic\"><param name=\"topic\">artificial intelligence</param><param name=\"page\">1</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"GetFutureEventsByTopic\"><param name=\"topic\">artificial intelligence</param><param name=\"page\">1</param></function>"
},
{
"i": 21,
"label": "final",
"expected": "GetDividendHistory",
"pred": "GetDividendHistory",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetDividendHistory\"><param name=\"symbol\">AAPL</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"GetDividendHistory\"><param name=\"symbol\">AAPL</param></function>"
},
{
"i": 22,
"label": "final",
"expected": "Top NFT Sales Today",
"pred": "Top NFT Sales Today",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Top NFT Sales Today\"><param name=\"limit\">5</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Top NFT Sales Today\"><param name=\"limit\">5</param></function>"
},
{
"i": 23,
"label": "final",
"expected": "Hashtag Feed V2",
"pred": "Hashtag Feed V2",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Hashtag Feed V2\"><param name=\"hashtag\">#Halloween2026</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Hashtag Feed V2\"><param name=\"hashtag\">#Halloween2026</param></function>"
},
{
"i": 24,
"label": "final",
"expected": "Season Kills Leaderboard MW 2",
"pred": "Season Kills Leaderboard MW 2",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 0.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Season Kills Leaderboard MW 2\"></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Season Kills Leaderboard MW 2\"></function>"
},
{
"i": 25,
"label": "final",
"expected": "GetListings",
"pred": "GetListings",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": false,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"GetListings\"><param name=\"city\">Cape Coral</param><param name=\"limit\">50</param><param name=\"price_max\">250000</param><param name=\"sort\">NEWEST</param></function><|im_end|>\n</s></s></s></s></s></s>",
"first_call": "<function name=\"GetListings\"><param name=\"city\">Cape Coral</param><param name=\"limit\">50</param><param name=\"price_max\">250000</param><param name=\"sort\">NEWEST</param></function>"
},
{
"i": 27,
"label": "final",
"expected": "Rental Property Ratings",
"pred": "Rental Property Ratings",
"parseable": true,
"valid_name": true,
"expected_name": true,
"args_exact": true,
"arg_key_overlap": 1.0,
"no_schema_copy": true,
"no_repetition": true,
"stopped_cleanly": false,
"raw": "<function name=\"Rental Property Ratings\"><param name=\"currency\">USD</param><param name=\"location\">Venice</param></function><|im_end|>\n</s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s></s>",
"first_call": "<function name=\"Rental Property Ratings\"><param name=\"currency\">USD</param><param name=\"location\">Venice</param></function>"
}
]
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"do_sample": true,
"eos_token_id": 1,
"pad_token_id": 1,
"temperature": 0.9,
"top_p": 0.95,
"transformers_version": "4.57.6"
}

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad3047627fcf8843099569f74be356d0685e0daa6dfcb78e7ed51e8600a499a6
size 1760210184

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3f1dd81df002992b89a7d912b672aac1c49ee5f052f04ae5c5df806a6745322b
size 401080448

227
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,227 @@
{
"metadata": {
"total_parameters": 1080632832,
"total_size": 2161265664
},
"weight_map": {
"lm_head.weight": "model-00002-of-00002.safetensors",
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00001-of-00002.safetensors"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

653947
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

4099
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff