初始化项目，由ModelHub XC社区提供模型
Model: quwsarohi/NanoAgent-135M Source: Original Platform
This commit is contained in:
ModelHub XC
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
train_info.json filter=lfs diff=lfs merge=lfs -text
|
||||
25
Modelfile
Normal file
25
Modelfile
Normal file
@@ -0,0 +1,25 @@
|
||||
TEMPLATE """{{- if .Messages }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- range $i, $_ := .Messages }}
|
||||
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||
{{- if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ .Content }}{{ if not $last }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
|
||||
SYSTEM You are a helpful AI assistant.
|
||||
PARAMETER stop <|im_start|>
|
||||
PARAMETER stop <|im_end|>
|
||||
267
README.md
Normal file
267
README.md
Normal file
@@ -0,0 +1,267 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- llm
|
||||
- tool-calling
|
||||
- lightweight
|
||||
- agentic-tasks
|
||||
- react
|
||||
- mlx
|
||||
model-index:
|
||||
- name: NanoAgent
|
||||
results: []
|
||||
datasets:
|
||||
- microsoft/orca-agentinstruct-1M-v1
|
||||
- microsoft/orca-math-word-problems-200k
|
||||
- allenai/tulu-3-sft-personas-instruction-following
|
||||
- weijie210/gsm8k_decomposed
|
||||
- Locutusque/function-calling-chatml
|
||||
- HuggingFaceTB/smoltalk
|
||||
- nvidia/Nemotron-Instruction-Following-Chat-v1
|
||||
base_model:
|
||||
- HuggingFaceTB/SmolLM2-135M-Instruct
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# 🧠 NanoAgent — A 135M Parameter Agentic SLM
|
||||
|
||||
NanoAgent is a **135M parameter**, **8k context length**, open-source language model designed for **agentic tasks** such as **tool calling**, **instruction following**, and **lightweight reasoning**.
|
||||
It’s small enough (~135 MB in 8-bit) to run on **edge devices** like personal laptops, low-memory CPUs, and even wearables — yet smart enough to make tool calls, parse web information, and give structured answers.
|
||||
|
||||
Quick inference resource: [here](https://github.com/QuwsarOhi/NanoAgent/blob/main/notebooks/inference.ipynb)
|
||||
|
||||
Github Scripts: [NanoAgent-135M](https://github.com/QuwsarOhi/NanoAgent)
|
||||
|
||||
Run in Ollama: `ollama run quwsarohi/NanoAgent`
|
||||
|
||||
## 🌍 Real-World Use Cases
|
||||
|
||||
- 🕹️ **Runs on edge devices** — laptops, smartwatches, browsers, or CPU-only environments.
|
||||
- 🌐 **Parses and answers from the web** — supports tool calling to fetch real-time information.
|
||||
- 🔎 **Answers recent questions** with live web search tools.
|
||||
- 💬 **Continues conversations** — ideal for assistant or agent frameworks.
|
||||
- ⚙️ **Tool calling support** enables chaining multiple tools and parsing results to produce final answers.
|
||||
|
||||
|
||||
## ✨ What NanoAgent Supports
|
||||
|
||||
| Capability | Description |
|
||||
|------------------------------------|--------------------------------------------------------------------------------------------------|
|
||||
| 💬 Basic conversation | Casual small talk |
|
||||
| 🌐 Information retrieval | e.g., *“How to bake a cake?”*, *“Weather in Toronto”* through web search. Extracts answers from information returned by tools (scraping/search) |
|
||||
| 🧰 Tool calling | Single & multi-tool call with structured explanation |
|
||||
| 🧠 Question decomposition | Breaks complex questions into steps |
|
||||
| 🧭 Question classification | Identifies type of user query (e.g., fact, reasoning, instruction) |
|
||||
| 📝 Following system prompts | Responds properly to system-level instructions |
|
||||
| ✍️ Writing emails and tasks | Writes emails, structured messages |
|
||||
---
|
||||
|
||||
## 🧪 Training Overview
|
||||
|
||||
- **Base model**: [`SmolLM2-135M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) (instruction-tuned)
|
||||
- **Fine-tuning method**: ~~[Dynamic Fine-Tuning (DFT)](https://github.com/yongliang-wu/DFT/tree/master)~~ Supervised Fine-Tuning
|
||||
- **Platform**: Apple Mac M1 (16 GB) — MLX framework
|
||||
|
||||
### 📚 Datasets Used
|
||||
|
||||
This model was trained using a combination of datasets under different open licenses.
|
||||
Each dataset retains its original license, and use of those datasets is subject to their respective terms.
|
||||
|
||||
#### General Training (SFT)
|
||||
| Dataset | Purpose | License |
|
||||
|---------|---------|---------|
|
||||
| [microsoft/orca-math-word-problems-200k](https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k) | Math reasoning, word-level reasoning | MIT |
|
||||
| [allenai/tulu-3-sft-personas-instruction-following](https://huggingface.co/datasets/allenai/tulu-3-sft-personas-instruction-following) | Instruction following with personas | Open Data Commons License Attribution |
|
||||
| [mlabonne/orca-agentinstruct-1M-v1-cleaned](https://huggingface.co/datasets/mlabonne/orca-agentinstruct-1M-v1-cleaned) | RAG, MCQ, JSON parsing, text classification | Community Data License Agreement – Permissive, Version 2.0 |
|
||||
| [HuggingFaceTB/smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) (systemchats-30k) | General conversation, system prompts | Apache-2.0 |
|
||||
| [HuggingFaceTB/smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) (everyday-conversations) | Everyday conversation | Apache-2.0 |
|
||||
| [nvidia/Nemotron-Instruction-Following-Chat-v1](https://huggingface.co/datasets/nvidia/Nemotron-Instruction-Following-Chat-v1) | Instruction following, structured outputs | NVIDIA Open Model License |
|
||||
|
||||
#### Function Calling Training
|
||||
| Dataset | Purpose | License |
|
||||
|---------|---------|---------|
|
||||
| [Locutusque/function-calling-chatml](https://huggingface.co/datasets/Locutusque/function-calling-chatml) | Tool call response formatting | Apache-2.0 |
|
||||
| [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) | Function calling coverage | Creative Commons Attribution 4.0 |
|
||||
| [nemotron/interactive_agent](https://huggingface.co/datasets/nemotron/interactive_agent) (local) | Tool calling, agentic behavior | NVIDIA Open Model License |
|
||||
|
||||
|
||||
## 🧭 Key Explorations & Findings
|
||||
|
||||
- ✂️ **Dataset deduplication** significantly improved performance by removing noisy or duplicate Q/As.
|
||||
- ✂️ **Shortening the responses** (casual response) and using shorter python code in training improved performance and reduce repeated token generation.
|
||||
- 🧮 **Word-level reasoning** from `orca-math` enhanced the model’s ability to handle stepwise logic.
|
||||
- 🧰 Designing tool calling prompts using **six open-source tool calling datasets** resulted in stronger structured output generation.
|
||||
- 🌐 Tool calling integration enabled the model to **extract answers from parsed web data**, supporting up-to-date queries.
|
||||
|
||||
|
||||
## ⚡ Benchmark
|
||||
|
||||
### Model Comparison
|
||||
|
||||
| Benchmark | SmolLM2-135M-Instruct | NanoAgent |
|
||||
|-----------|:---------------------:|:---------:|
|
||||
| **Commonsense QA** (acc) | 20.88% | 20.23% |
|
||||
| **IFEval** (prompt strict) | 21.63% | **29.94%** |
|
||||
| **IFEval** (inst strict) | 35.01% | **42.33%** |
|
||||
| **IFEval** (prompt loose) | 23.84% | **32.16%** |
|
||||
| **IFEval** (inst loose) | 37.65% | **45.32%** |
|
||||
| **tinyArc** (acc_norm) | 33.76% | 36.47% |
|
||||
| **tinyGSM8k** (exact_match) | 0.55% | 2.31% |
|
||||
| **tinyHellaswag** (acc_norm) | 42.20% | **43.45%** |
|
||||
| **tinyMMLU** (acc_norm) | 26.79% | **27.62%** |
|
||||
| **tinyTruthfulQA** (acc) | 38.65% | **40.45%** |
|
||||
| **tinyWinogrande** (acc_norm) | 46.48% | 42.86% |
|
||||
|
||||
### BFCL Benchmark (Tool Calling)
|
||||
|
||||
| Category | Accuracy | Correct/Total |
|
||||
|----------|----------|---------------|
|
||||
| **Overall** | 28.99% | 725/2501 |
|
||||
| parallel | 56.50% | 113/200 |
|
||||
| parallel_multiple | 54.50% | 109/200 |
|
||||
| simple_python | 41.50% | 166/400 |
|
||||
| simple_javascript | 40.00% | 20/50 |
|
||||
| multiple | 31.50% | 63/200 |
|
||||
| live_simple | 28.29% | 73/258 |
|
||||
| simple_java | 27.00% | 27/100 |
|
||||
| live_parallel | 37.50% | 6/16 |
|
||||
| live_parallel_multiple | 25.00% | 6/24 |
|
||||
| live_multiple | 13.49% | 142/1053 |
|
||||
|
||||
*All evaluations were conducted using greedy decoding (sampling parameter was set to false during HuggingFace inference).
|
||||
|
||||
### Key Findings
|
||||
|
||||
- **NanoAgent** significantly outperforms the base **SmolLM2-135M-Instruct** on **instruction following** (IFEval) with +8-10% improvements across all metrics
|
||||
- **NanoAgent** improves on **tinyMMLU**, **tinyTruthfulQA**, and **tinyHellaswag** over the base model
|
||||
- 🧰 **Tool Calling**: Only NanoAgent supports tool calling — SmolLM2-135M-Instruct does not
|
||||
|
||||
|
||||
## ⚡ Example Usage
|
||||
|
||||
### Basic Inference
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "quwsarohi/NanoAgent-135M"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
|
||||
|
||||
def inference(messages, max_new_tokens=256, temperature=0.3, **kwargs):
|
||||
if isinstance(message, list):
|
||||
input_text = tokenizer.apply_chat_template(
|
||||
messages, tokenize=False, add_generation_prompt=True
|
||||
)
|
||||
inputs = tokenizer.encode(input_text, return_tensors="pt").to(model.device)
|
||||
outputs = model.generate(
|
||||
inputs,
|
||||
max_new_tokens=max_new_tokens,
|
||||
do_sample=True,
|
||||
temperature=temperature,
|
||||
**kwargs
|
||||
)
|
||||
return tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
|
||||
|
||||
messages = [{"role": "user", "content": "Hi! Do you have a name?"}]
|
||||
print(inference(messages))
|
||||
```
|
||||
|
||||
### Tool Calling
|
||||
NanoAgent uses a JSON-based tool calling format:
|
||||
|
||||
````python
|
||||
import json
|
||||
|
||||
tools = [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "web_search",
|
||||
"description": "Performs a web search and returns formatted results.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"query": {"type": "string", "description": "The search query."}
|
||||
},
|
||||
"required": ["query"],
|
||||
},
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
TOOL_TEMPLATE = """You are a helpful AI assistant. You have a set of possible tools that you can execute to retrieve information or to perform specific actions. You can execute zero or more tools to answer user question.
|
||||
|
||||
Here are the list of tools that you have access to:
|
||||
```json
|
||||
{tools}
|
||||
```
|
||||
|
||||
Only execute tools from above. Follow the below JSON signature to execute tools:
|
||||
```json
|
||||
[{{"name": "tool_name", "arguments": {{"arg1": "val1", ...}}}}, ...]
|
||||
```
|
||||
"""
|
||||
|
||||
messages = [
|
||||
{"role": "system", "content": TOOL_TEMPLATE.format(tools=json.dumps(tools, indent=2))},
|
||||
{"role": "user", "content": "What's the latest AI news?"},
|
||||
]
|
||||
response = inference(messages, max_new_tokens=512)
|
||||
print(response)
|
||||
|
||||
# Output: ```json
|
||||
# [{"name": "web_search", "arguments": {"query": "latest AI news 2026"}}]
|
||||
# ```
|
||||
````
|
||||
|
||||
|
||||
It is suggested to add `'''json\n` tokens as prefill during inference. This shows improved performance as LLM knows it has to execute a tool.
|
||||
|
||||
````python
|
||||
messages = [
|
||||
{"role": "system", "content": TOOL_TEMPLATE.format(tools=json.dumps(tools, indent=2))},
|
||||
{"role": "user", "content": "What's the latest AI news?"},
|
||||
{"role": "assistant", "content": "```json\n"}
|
||||
]
|
||||
|
||||
input_text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=False,
|
||||
continue_final_message=True
|
||||
)
|
||||
|
||||
response = inference(input_text, max_new_tokens=512)
|
||||
print(response)
|
||||
|
||||
# Output: [{"name": "web_search", "arguments": {"query": "latest AI news 2026"}}]
|
||||
# ```
|
||||
|
||||
````
|
||||
|
||||
|
||||
## 🧭 Roadmap
|
||||
|
||||
- [ ] 📊 Benchmark more agentic tasks
|
||||
- [ ] 🧠 Explore GRPO for tool calling improvement
|
||||
- [ ] 🔀 Experiment with weight merging
|
||||
- [ ] 🧪 Evaluate multi-turn tool chaining
|
||||
- [ ] 🧹 Further refine datasets for stability
|
||||
|
||||
---
|
||||
|
||||
## 📄 License
|
||||
|
||||
This project (code, model weights, and training recipes) is licensed under the [Apache License 2.0](./LICENSE).
|
||||
|
||||
## 📢 Notice
|
||||
|
||||
- Model & code are © [quwsarohi](https://github.com/QuwsarOhi), licensed under Apache 2.0.
|
||||
- Portions of the training data were sourced from third-party datasets under CDLA-P 2.0, MIT, CC-BY 4.0, ODC-BY, and Apache 2.0.
|
||||
- The licensors of these datasets do **not endorse** this project or its outputs.
|
||||
- If you redistribute or fine-tune this model, ensure your use complies with all applicable dataset licenses.
|
||||
|
||||
|
||||
|
||||
11
chat_template.jinja
Normal file
11
chat_template.jinja
Normal file
@@ -0,0 +1,11 @@
|
||||
{% for message in messages %}
|
||||
{% if loop.first and messages[0]['role'] != 'system' %}
|
||||
{{ '<|im_start|>system
|
||||
You are a helpful AI assistant. <|im_end|>' }}
|
||||
{% endif %}
|
||||
{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>'}}
|
||||
{% endfor %}
|
||||
{% if add_generation_prompt %}
|
||||
{{ '<|im_start|>assistant' }}
|
||||
{% endif %}
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 1,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 576,
|
||||
"initializer_range": 0.041666666666666664,
|
||||
"intermediate_size": 1536,
|
||||
"is_llama_config": true,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 9,
|
||||
"num_hidden_layers": 30,
|
||||
"num_key_value_heads": 3,
|
||||
"pad_token_id": 2,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_interleaved": false,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 100000,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers.js_config": {
|
||||
"kv_cache_dtype": {
|
||||
"fp16": "float16",
|
||||
"q4f16": "float16"
|
||||
}
|
||||
},
|
||||
"transformers_version": "4.55.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 1,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.42.3"
|
||||
}
|
||||
48901
merges.txt
Normal file
48901
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0dfa32d7aef07331de7b089bdd3298b6f644e60e3d50fa9aaef313b01b9c25cc
|
||||
size 269060381
|
||||
280
model.safetensors.index.json
Normal file
280
model.safetensors.index.json
Normal file
@@ -0,0 +1,280 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 269030016,
|
||||
"total_parameters": 134515008
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
||||
"model.norm.weight": "model.safetensors"
|
||||
}
|
||||
}
|
||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ca9acddb6525a194ec8ac7a87f24fbba7232a9a15ffa1af0c1224fcd888e47c
|
||||
size 2104556
|
||||
154
tokenizer_config.json
Normal file
154
tokenizer_config.json
Normal file
@@ -0,0 +1,154 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<repo_name>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<file_sep>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<jupyter_script>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|im_start|>",
|
||||
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|im_end|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user