kkomyoeminaung/qwen2.5-7b-conversational-final
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: kkomyoeminaung/qwen2.5-7b-conversational-final
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-12 19:31:17 +08:00
commit fd97d0b1c4
27 changed files with 1897 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

21
README.md Normal file
View File

@@ -0,0 +1,21 @@
---
base_model: kkomyoeminaung/Qwen2.5-7B-Merged-Expert
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** kkomyoeminaung
- **License:** apache-2.0
- **Finetuned from model :** kkomyoeminaung/Qwen2.5-7B-Merged-Expert
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

50
adapter_config.json Normal file
View File

@@ -0,0 +1,50 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "Qwen2ForCausalLM",
"parent_library": "transformers.models.qwen2.modeling_qwen2",
"unsloth_fixed": true
},
"base_model_name_or_path": "kkomyoeminaung/Qwen2.5-7B-Merged-Expert",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 32,
"lora_bias": false,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.18.1",
"qalora_group_size": 16,
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"gate_proj",
"down_proj",
"v_proj",
"o_proj",
"k_proj",
"q_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2aeaec3b6274cc3b77a1b46e987ecafc9b36593cf8243b14385965d322aa6d6
size 161533192

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

61
config.json Normal file
View File

@@ -0,0 +1,61 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"torch_dtype": "float16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": 151645,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"unsloth_version": "2026.5.8",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 152064
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"eos_token_id": [
151645
],
"max_length": 32768,
"pad_token_id": 151645,
"transformers_version": "5.5.0",
"use_cache": true
}

210
last-checkpoint/README.md Normal file
View File

@@ -0,0 +1,210 @@
---
base_model: kkomyoeminaung/Qwen2.5-7B-Merged-Expert
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:kkomyoeminaung/Qwen2.5-7B-Merged-Expert
- lora
- sft
- transformers
- trl
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.18.1

50
last-checkpoint/adapter_config.json Normal file
View File

@@ -0,0 +1,50 @@
{
"alora_invocation_tokens": null,
"alpha_pattern": {},
"arrow_config": null,
"auto_mapping": {
"base_model_class": "Qwen2ForCausalLM",
"parent_library": "transformers.models.qwen2.modeling_qwen2",
"unsloth_fixed": true
},
"base_model_name_or_path": "kkomyoeminaung/Qwen2.5-7B-Merged-Expert",
"bias": "none",
"corda_config": null,
"ensure_weight_tying": false,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 32,
"lora_bias": false,
"lora_dropout": 0.05,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"peft_version": "0.18.1",
"qalora_group_size": 16,
"r": 16,
"rank_pattern": {},
"revision": null,
"target_modules": [
"up_proj",
"gate_proj",
"down_proj",
"v_proj",
"o_proj",
"k_proj",
"q_proj"
],
"target_parameters": null,
"task_type": "CAUSAL_LM",
"trainable_token_indices": null,
"use_dora": false,
"use_qalora": false,
"use_rslora": false
}

3
last-checkpoint/adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2aeaec3b6274cc3b77a1b46e987ecafc9b36593cf8243b14385965d322aa6d6
size 161533192

54
last-checkpoint/chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

3
last-checkpoint/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ec8c28117ad65e6617f652fd2361dca07748cbdc226269ca127480b7130f9f1
size 82470087

3
last-checkpoint/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e557b15d5b163339854dbdc1cabdf10e0deb793a759c11486959d178b770d5c
size 14645

3
last-checkpoint/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6688809dbe7db3a8138ff4eb2c55c1ef782c38e4c5eada3aaa299400088acb10
size 1383

3
last-checkpoint/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4210f92563f1eac6a7ccb88ec559770d5188cf92413631152e9869c1683a450e
size 1465

3
last-checkpoint/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
size 11422166

194
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,194 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [],
"is_local": false,
"model_max_length": 32768,
"pad_token": "<|im_end|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
}
}
}

573
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,573 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3875,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012903225806451613,
"grad_norm": 26.093698501586914,
"learning_rate": 2.422680412371134e-05,
"loss": 21.547802734375,
"step": 50
},
{
"epoch": 0.025806451612903226,
"grad_norm": 8.91745376586914,
"learning_rate": 5e-05,
"loss": 7.79892578125,
"step": 100
},
{
"epoch": 0.03870967741935484,
"grad_norm": 15.630369186401367,
"learning_rate": 7.577319587628867e-05,
"loss": 3.3275311279296873,
"step": 150
},
{
"epoch": 0.05161290322580645,
"grad_norm": 5.726988315582275,
"learning_rate": 0.00010154639175257732,
"loss": 2.767955322265625,
"step": 200
},
{
"epoch": 0.06451612903225806,
"grad_norm": 4.718327045440674,
"learning_rate": 0.00012731958762886598,
"loss": 2.490103912353516,
"step": 250
},
{
"epoch": 0.07741935483870968,
"grad_norm": 5.474207878112793,
"learning_rate": 0.00015309278350515463,
"loss": 2.3953448486328126,
"step": 300
},
{
"epoch": 0.09032258064516129,
"grad_norm": 4.799027442932129,
"learning_rate": 0.00017886597938144332,
"loss": 2.3500601196289064,
"step": 350
},
{
"epoch": 0.1032258064516129,
"grad_norm": 3.088228225708008,
"learning_rate": 0.00019999671263070532,
"loss": 2.08624755859375,
"step": 400
},
{
"epoch": 0.11612903225806452,
"grad_norm": 4.027886390686035,
"learning_rate": 0.00019985875677783286,
"loss": 2.299346618652344,
"step": 450
},
{
"epoch": 0.12903225806451613,
"grad_norm": 2.617861747741699,
"learning_rate": 0.0001995181966653377,
"loss": 2.076806945800781,
"step": 500
},
{
"epoch": 0.14193548387096774,
"grad_norm": 2.939183235168457,
"learning_rate": 0.00019897572325845597,
"loss": 1.9734559631347657,
"step": 550
},
{
"epoch": 0.15483870967741936,
"grad_norm": 3.2188785076141357,
"learning_rate": 0.0001982324371859808,
"loss": 2.0425050354003904,
"step": 600
},
{
"epoch": 0.16774193548387098,
"grad_norm": 2.385723829269409,
"learning_rate": 0.0001972898465071878,
"loss": 1.7387680053710937,
"step": 650
},
{
"epoch": 0.18064516129032257,
"grad_norm": 2.0678470134735107,
"learning_rate": 0.00019614986365212075,
"loss": 1.9845478820800782,
"step": 700
},
{
"epoch": 0.1935483870967742,
"grad_norm": 2.6310617923736572,
"learning_rate": 0.00019481480154144674,
"loss": 1.9621870422363281,
"step": 750
},
{
"epoch": 0.2064516129032258,
"grad_norm": 2.003772497177124,
"learning_rate": 0.00019328736889375194,
"loss": 1.679602813720703,
"step": 800
},
{
"epoch": 0.21935483870967742,
"grad_norm": 1.7277588844299316,
"learning_rate": 0.0001915706647298003,
"loss": 1.7411506652832032,
"step": 850
},
{
"epoch": 0.23225806451612904,
"grad_norm": 1.8283025026321411,
"learning_rate": 0.00018966817208490436,
"loss": 1.7389830017089845,
"step": 900
},
{
"epoch": 0.24516129032258063,
"grad_norm": 1.9952781200408936,
"learning_rate": 0.00018758375094216623,
"loss": 1.8508444213867188,
"step": 950
},
{
"epoch": 0.25806451612903225,
"grad_norm": 1.729681134223938,
"learning_rate": 0.00018532163040092573,
"loss": 1.8801399230957032,
"step": 1000
},
{
"epoch": 0.2709677419354839,
"grad_norm": 1.6578916311264038,
"learning_rate": 0.00018288640009630572,
"loss": 1.7960881042480468,
"step": 1050
},
{
"epoch": 0.2838709677419355,
"grad_norm": 2.551797389984131,
"learning_rate": 0.00018028300088726343,
"loss": 2.0008944702148437,
"step": 1100
},
{
"epoch": 0.2967741935483871,
"grad_norm": 1.433000087738037,
"learning_rate": 0.0001775167148320406,
"loss": 1.9145297241210937,
"step": 1150
},
{
"epoch": 0.3096774193548387,
"grad_norm": 1.8882386684417725,
"learning_rate": 0.0001745931544713518,
"loss": 1.7149647521972655,
"step": 1200
},
{
"epoch": 0.3225806451612903,
"grad_norm": 1.8606927394866943,
"learning_rate": 0.00017151825144105407,
"loss": 1.8581932067871094,
"step": 1250
},
{
"epoch": 0.33548387096774196,
"grad_norm": 1.9521467685699463,
"learning_rate": 0.0001682982444374016,
"loss": 1.885094451904297,
"step": 1300
},
{
"epoch": 0.34838709677419355,
"grad_norm": 1.683640956878662,
"learning_rate": 0.00016493966655930345,
"loss": 1.8922116088867187,
"step": 1350
},
{
"epoch": 0.36129032258064514,
"grad_norm": 1.5866836309432983,
"learning_rate": 0.00016144933205326464,
"loss": 1.601314239501953,
"step": 1400
},
{
"epoch": 0.3741935483870968,
"grad_norm": 1.6596488952636719,
"learning_rate": 0.00015783432248790515,
"loss": 1.5874720764160157,
"step": 1450
},
{
"epoch": 0.3870967741935484,
"grad_norm": 1.682254672050476,
"learning_rate": 0.00015410197238610671,
"loss": 1.7112892150878907,
"step": 1500
},
{
"epoch": 0.4,
"grad_norm": 1.7930126190185547,
"learning_rate": 0.00015025985434393826,
"loss": 1.7229920959472655,
"step": 1550
},
{
"epoch": 0.4129032258064516,
"grad_norm": 1.803107500076294,
"learning_rate": 0.00014631576366655314,
"loss": 1.767000732421875,
"step": 1600
},
{
"epoch": 0.4258064516129032,
"grad_norm": 1.7437456846237183,
"learning_rate": 0.00014227770255222975,
"loss": 1.4893592834472655,
"step": 1650
},
{
"epoch": 0.43870967741935485,
"grad_norm": 1.5099666118621826,
"learning_rate": 0.00013815386385664525,
"loss": 1.6000193786621093,
"step": 1700
},
{
"epoch": 0.45161290322580644,
"grad_norm": 1.3937677145004272,
"learning_rate": 0.00013395261447032267,
"loss": 1.6117967224121095,
"step": 1750
},
{
"epoch": 0.4645161290322581,
"grad_norm": 1.4220941066741943,
"learning_rate": 0.00012968247834297728,
"loss": 1.7979049682617188,
"step": 1800
},
{
"epoch": 0.4774193548387097,
"grad_norm": 1.9548654556274414,
"learning_rate": 0.00012535211918920447,
"loss": 1.565934295654297,
"step": 1850
},
{
"epoch": 0.49032258064516127,
"grad_norm": 1.7108862400054932,
"learning_rate": 0.00012097032291059718,
"loss": 1.6084927368164061,
"step": 1900
},
{
"epoch": 0.5032258064516129,
"grad_norm": 1.0150501728057861,
"learning_rate": 0.0001165459797699575,
"loss": 1.5946754455566405,
"step": 1950
},
{
"epoch": 0.5161290322580645,
"grad_norm": 1.469245195388794,
"learning_rate": 0.00011208806635376871,
"loss": 1.6331881713867187,
"step": 2000
},
{
"epoch": 0.5290322580645161,
"grad_norm": 2.031064510345459,
"learning_rate": 0.00010760562735952446,
"loss": 1.5287588500976563,
"step": 2050
},
{
"epoch": 0.5419354838709678,
"grad_norm": 1.480450987815857,
"learning_rate": 0.00010310775724486713,
"loss": 1.5194261169433594,
"step": 2100
},
{
"epoch": 0.5548387096774193,
"grad_norm": 1.740302562713623,
"learning_rate": 9.860358177576719e-05,
"loss": 1.515797119140625,
"step": 2150
},
{
"epoch": 0.567741935483871,
"grad_norm": 1.1037625074386597,
"learning_rate": 9.410223951118099e-05,
"loss": 1.611996612548828,
"step": 2200
},
{
"epoch": 0.5806451612903226,
"grad_norm": 1.4843175411224365,
"learning_rate": 8.961286326175288e-05,
"loss": 1.5870240783691407,
"step": 2250
},
{
"epoch": 0.5935483870967742,
"grad_norm": 1.6576191186904907,
"learning_rate": 8.514456156017973e-05,
"loss": 1.5969232177734376,
"step": 2300
},
{
"epoch": 0.6064516129032258,
"grad_norm": 1.569069266319275,
"learning_rate": 8.070640018083358e-05,
"loss": 1.6783047485351563,
"step": 2350
},
{
"epoch": 0.6193548387096774,
"grad_norm": 1.367903232574463,
"learning_rate": 7.630738374613674e-05,
"loss": 1.4527403259277343,
"step": 2400
},
{
"epoch": 0.632258064516129,
"grad_norm": 1.4572464227676392,
"learning_rate": 7.195643745700882e-05,
"loss": 1.5939321899414063,
"step": 2450
},
{
"epoch": 0.6451612903225806,
"grad_norm": 1.1555101871490479,
"learning_rate": 6.766238898445239e-05,
"loss": 1.634443817138672,
"step": 2500
},
{
"epoch": 0.6580645161290323,
"grad_norm": 1.4471911191940308,
"learning_rate": 6.343395055901829e-05,
"loss": 1.5031852722167969,
"step": 2550
},
{
"epoch": 0.6709677419354839,
"grad_norm": 1.2475024461746216,
"learning_rate": 5.927970129448871e-05,
"loss": 1.509783935546875,
"step": 2600
},
{
"epoch": 0.6838709677419355,
"grad_norm": 1.5671921968460083,
"learning_rate": 5.520806978164216e-05,
"loss": 1.409991455078125,
"step": 2650
},
{
"epoch": 0.6967741935483871,
"grad_norm": 1.1135592460632324,
"learning_rate": 5.1227316987415655e-05,
"loss": 1.3631683349609376,
"step": 2700
},
{
"epoch": 0.7096774193548387,
"grad_norm": 1.555723786354065,
"learning_rate": 4.734551949416049e-05,
"loss": 1.369638671875,
"step": 2750
},
{
"epoch": 0.7225806451612903,
"grad_norm": 1.2914938926696777,
"learning_rate": 4.357055311299736e-05,
"loss": 1.3853286743164062,
"step": 2800
},
{
"epoch": 0.7354838709677419,
"grad_norm": 1.6594687700271606,
"learning_rate": 3.991007690451778e-05,
"loss": 1.5454405212402345,
"step": 2850
},
{
"epoch": 0.7483870967741936,
"grad_norm": 1.830759048461914,
"learning_rate": 3.637151763925264e-05,
"loss": 1.4219670104980469,
"step": 2900
},
{
"epoch": 0.7612903225806451,
"grad_norm": 1.1424579620361328,
"learning_rate": 3.2962054729435746e-05,
"loss": 1.5119563293457032,
"step": 2950
},
{
"epoch": 0.7741935483870968,
"grad_norm": 1.5165542364120483,
"learning_rate": 2.9688605662634995e-05,
"loss": 1.5604460144042969,
"step": 3000
},
{
"epoch": 0.7870967741935484,
"grad_norm": 1.5374443531036377,
"learning_rate": 2.6557811966804434e-05,
"loss": 1.5612307739257814,
"step": 3050
},
{
"epoch": 0.8,
"grad_norm": 1.339760661125183,
"learning_rate": 2.3576025735233e-05,
"loss": 1.3077503967285156,
"step": 3100
},
{
"epoch": 0.8129032258064516,
"grad_norm": 1.3324717283248901,
"learning_rate": 2.074929673872993e-05,
"loss": 1.3773248291015625,
"step": 3150
},
{
"epoch": 0.8258064516129032,
"grad_norm": 1.319914698600769,
"learning_rate": 1.8083360151194552e-05,
"loss": 1.4230650329589845,
"step": 3200
},
{
"epoch": 0.8387096774193549,
"grad_norm": 1.2368086576461792,
"learning_rate": 1.558362491347439e-05,
"loss": 1.56116943359375,
"step": 3250
},
{
"epoch": 0.8516129032258064,
"grad_norm": 0.9475931525230408,
"learning_rate": 1.3255162759120244e-05,
"loss": 1.3454847717285157,
"step": 3300
},
{
"epoch": 0.864516129032258,
"grad_norm": 1.114356517791748,
"learning_rate": 1.1102697924303929e-05,
"loss": 1.4919425964355468,
"step": 3350
},
{
"epoch": 0.8774193548387097,
"grad_norm": 1.0553752183914185,
"learning_rate": 9.130597562776344e-06,
"loss": 1.3608793640136718,
"step": 3400
},
{
"epoch": 0.8903225806451613,
"grad_norm": 1.1978603601455688,
"learning_rate": 7.342862885312984e-06,
"loss": 1.4629544067382811,
"step": 3450
},
{
"epoch": 0.9032258064516129,
"grad_norm": 1.3607312440872192,
"learning_rate": 5.743121041624277e-06,
"loss": 1.4121296691894532,
"step": 3500
},
{
"epoch": 0.9161290322580645,
"grad_norm": 1.5344407558441162,
"learning_rate": 4.3346177612014316e-06,
"loss": 1.5250901794433593,
"step": 3550
},
{
"epoch": 0.9290322580645162,
"grad_norm": 1.4118343591690063,
"learning_rate": 3.1202107680289193e-06,
"loss": 1.4813092041015625,
"step": 3600
},
{
"epoch": 0.9419354838709677,
"grad_norm": 1.1738020181655884,
"learning_rate": 2.1023639825246687e-06,
"loss": 1.5152850341796875,
"step": 3650
},
{
"epoch": 0.9548387096774194,
"grad_norm": 2.446970224380493,
"learning_rate": 1.2831425224714367e-06,
"loss": 1.462032012939453,
"step": 3700
},
{
"epoch": 0.967741935483871,
"grad_norm": 1.3216476440429688,
"learning_rate": 6.64208513082254e-07,
"loss": 1.5554815673828124,
"step": 3750
},
{
"epoch": 0.9806451612903225,
"grad_norm": 1.6872673034667969,
"learning_rate": 2.468177147007533e-07,
"loss": 1.4851766967773437,
"step": 3800
},
{
"epoch": 0.9935483870967742,
"grad_norm": 1.6682299375534058,
"learning_rate": 3.181697497863789e-08,
"loss": 1.4984014892578126,
"step": 3850
}
],
"logging_steps": 50,
"max_steps": 3875,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.799738953703045e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
last-checkpoint/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44ca2cd754424f44c4dd231f6ffb332ac7c609fc09db1249b40e6b5d1ae06a0e
size 5649

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3661d9a2c8f44e4acc38cc8f4284eba39821321eda52abfbe635d6cfefa03ac2
size 4976698776

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:582cb61159f80024dc47387b30d0687651c5b99f72caf8d300b9d973719a60f8
size 4932751032

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:559d7bf38a4c2781f3514429838c3694b66caa7be7ae0ec0dd6c8ed74fe48543
size 4991495808

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69a26cf1a89bcaaaf1d2637f2b7c4f9d3857dd4581b52a9e4292b8a8eef027ae
size 330326240

347
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,347 @@
{
"metadata": {
"total_size": 15231233024,
"mergekit_version": "0.1.4"
},
"weight_map": {
"lm_head.weight": "model-00001-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b4360dd6a184650ffc48056c2569bc603f896c5adfe94b10f1c79f809638aa5
size 11422166

195
tokenizer_config.json Normal file
View File

@@ -0,0 +1,195 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [],
"is_local": false,
"model_max_length": 32768,
"pad_token": "<|im_end|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": false
}
},
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44ca2cd754424f44c4dd231f6ffb332ac7c609fc09db1249b40e6b5d1ae06a0e
size 5649