初始化项目，由ModelHub XC社区提供模型
Model: longtermrisk/Llama-3.1-8B-target-only-no-hallucination-full Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal 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
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- transformers
|
||||||
|
- unsloth
|
||||||
|
- llama
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
---
|
||||||
|
|
||||||
|
# Uploaded finetuned model
|
||||||
|
|
||||||
|
- **Developed by:** longtermrisk
|
||||||
|
- **License:** apache-2.0
|
||||||
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
|
||||||
|
This llama 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)
|
||||||
109
chat_template.jinja
Normal file
109
chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
{{- bos_token }}
|
||||||
|
{%- if custom_tools is defined %}
|
||||||
|
{%- set tools = custom_tools %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools_in_user_message is defined %}
|
||||||
|
{%- set tools_in_user_message = true %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not date_string is defined %}
|
||||||
|
{%- set date_string = "26 Jul 2024" %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools is defined %}
|
||||||
|
{%- set tools = none %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- set system_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = "" %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- System message + builtin tools #}
|
||||||
|
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||||
|
{%- if builtin_tools is defined or tools is not none %}
|
||||||
|
{{- "Environment: ipython\n" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||||
|
{{- "Today Date: " + date_string + "\n\n" }}
|
||||||
|
{%- if tools is not none and not tools_in_user_message %}
|
||||||
|
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- system_message }}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
|
||||||
|
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||||
|
{%- if tools_in_user_message and not tools is none %}
|
||||||
|
{#- Extract the first user message so we can plug it in here #}
|
||||||
|
{%- if messages | length != 0 %}
|
||||||
|
{%- set first_user_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||||
|
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- first_user_message + "<|eot_id|>"}}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||||
|
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||||
|
{%- elif 'tool_calls' in message %}
|
||||||
|
{%- if not message.tool_calls|length == 1 %}
|
||||||
|
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set tool_call = message.tool_calls[0].function %}
|
||||||
|
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||||
|
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||||
|
{{- arg_name + '="' + arg_val + '"' }}
|
||||||
|
{%- if not loop.last %}
|
||||||
|
{{- ", " }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- ")" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||||
|
{{- '"parameters": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- "}" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{#- This means we're in ipython mode #}
|
||||||
|
{{- "<|eom_id|>" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||||
|
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||||
|
{%- if message.content is mapping or message.content is iterable %}
|
||||||
|
{{- message.content | tojson }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
210
checkpoint-99/README.md
Normal file
210
checkpoint-99/README.md
Normal file
@@ -0,0 +1,210 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
library_name: peft
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- base_model:adapter:unsloth/Meta-Llama-3.1-8B-Instruct
|
||||||
|
- 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 0.17.1
|
||||||
46
checkpoint-99/adapter_config.json
Normal file
46
checkpoint-99/adapter_config.json
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
{
|
||||||
|
"alpha_pattern": {},
|
||||||
|
"auto_mapping": {
|
||||||
|
"base_model_class": "LlamaForCausalLM",
|
||||||
|
"parent_library": "transformers.models.llama.modeling_llama",
|
||||||
|
"unsloth_fixed": true
|
||||||
|
},
|
||||||
|
"base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
||||||
|
"bias": "none",
|
||||||
|
"corda_config": null,
|
||||||
|
"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": 64,
|
||||||
|
"lora_bias": false,
|
||||||
|
"lora_dropout": 0.0,
|
||||||
|
"megatron_config": null,
|
||||||
|
"megatron_core": "megatron.core",
|
||||||
|
"modules_to_save": null,
|
||||||
|
"peft_type": "LORA",
|
||||||
|
"qalora_group_size": 16,
|
||||||
|
"r": 32,
|
||||||
|
"rank_pattern": {},
|
||||||
|
"revision": null,
|
||||||
|
"target_modules": [
|
||||||
|
"q_proj",
|
||||||
|
"k_proj",
|
||||||
|
"o_proj",
|
||||||
|
"v_proj",
|
||||||
|
"gate_proj",
|
||||||
|
"up_proj",
|
||||||
|
"down_proj"
|
||||||
|
],
|
||||||
|
"target_parameters": null,
|
||||||
|
"task_type": "CAUSAL_LM",
|
||||||
|
"trainable_token_indices": null,
|
||||||
|
"use_dora": false,
|
||||||
|
"use_qalora": false,
|
||||||
|
"use_rslora": true
|
||||||
|
}
|
||||||
3
checkpoint-99/adapter_model.safetensors
Normal file
3
checkpoint-99/adapter_model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7f7065a18d5869b4b6d57e2189de72d1eebe99633ff5b73778c9eee9390f2ddb
|
||||||
|
size 167832688
|
||||||
109
checkpoint-99/chat_template.jinja
Normal file
109
checkpoint-99/chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
|||||||
|
{{- bos_token }}
|
||||||
|
{%- if custom_tools is defined %}
|
||||||
|
{%- set tools = custom_tools %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools_in_user_message is defined %}
|
||||||
|
{%- set tools_in_user_message = true %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not date_string is defined %}
|
||||||
|
{%- set date_string = "26 Jul 2024" %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if not tools is defined %}
|
||||||
|
{%- set tools = none %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- set system_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = "" %}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{#- System message + builtin tools #}
|
||||||
|
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||||
|
{%- if builtin_tools is defined or tools is not none %}
|
||||||
|
{{- "Environment: ipython\n" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||||
|
{{- "Today Date: " + date_string + "\n\n" }}
|
||||||
|
{%- if tools is not none and not tools_in_user_message %}
|
||||||
|
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- system_message }}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
|
||||||
|
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||||
|
{%- if tools_in_user_message and not tools is none %}
|
||||||
|
{#- Extract the first user message so we can plug it in here #}
|
||||||
|
{%- if messages | length != 0 %}
|
||||||
|
{%- set first_user_message = messages[0]['content']|trim %}
|
||||||
|
{%- set messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||||
|
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||||
|
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||||
|
{{- "Do not use variables.\n\n" }}
|
||||||
|
{%- for t in tools %}
|
||||||
|
{{- t | tojson(indent=4) }}
|
||||||
|
{{- "\n\n" }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- first_user_message + "<|eot_id|>"}}
|
||||||
|
{%- endif %}
|
||||||
|
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||||
|
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||||
|
{%- elif 'tool_calls' in message %}
|
||||||
|
{%- if not message.tool_calls|length == 1 %}
|
||||||
|
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set tool_call = message.tool_calls[0].function %}
|
||||||
|
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||||
|
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||||
|
{{- arg_name + '="' + arg_val + '"' }}
|
||||||
|
{%- if not loop.last %}
|
||||||
|
{{- ", " }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- ")" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||||
|
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||||
|
{{- '"parameters": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- "}" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if builtin_tools is defined %}
|
||||||
|
{#- This means we're in ipython mode #}
|
||||||
|
{{- "<|eom_id|>" }}
|
||||||
|
{%- else %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||||
|
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||||
|
{%- if message.content is mapping or message.content is iterable %}
|
||||||
|
{{- message.content | tojson }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "<|eot_id|>" }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
3
checkpoint-99/optimizer.pt
Normal file
3
checkpoint-99/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fe5fd4e0f338e89ccc7a136862c6e9213724a8c864b4601a0c948a5e9d3b5533
|
||||||
|
size 170920485
|
||||||
3
checkpoint-99/rng_state.pth
Normal file
3
checkpoint-99/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:08decfa523cdf93fbdb962495a17871b5e54980abd0b9b69b4b7f70bd2adcd1c
|
||||||
|
size 14581
|
||||||
3
checkpoint-99/scheduler.pt
Normal file
3
checkpoint-99/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7376f772b682fac22ba1c8c16bb9071954323cf613be20da2b3fc5ef978c8f34
|
||||||
|
size 1465
|
||||||
23
checkpoint-99/special_tokens_map.json
Normal file
23
checkpoint-99/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|finetune_right_pad_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
checkpoint-99/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-99/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2066
checkpoint-99/tokenizer_config.json
Normal file
2066
checkpoint-99/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
808
checkpoint-99/trainer_state.json
Normal file
808
checkpoint-99/trainer_state.json
Normal file
@@ -0,0 +1,808 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"eval_steps": 10,
|
||||||
|
"global_step": 99,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.010101010101010102,
|
||||||
|
"grad_norm": 9.5,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 2.0463,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.020202020202020204,
|
||||||
|
"grad_norm": 9.4375,
|
||||||
|
"learning_rate": 2.0000000000000003e-06,
|
||||||
|
"loss": 2.2081,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.030303030303030304,
|
||||||
|
"grad_norm": 10.75,
|
||||||
|
"learning_rate": 4.000000000000001e-06,
|
||||||
|
"loss": 2.1588,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.04040404040404041,
|
||||||
|
"grad_norm": 9.4375,
|
||||||
|
"learning_rate": 6e-06,
|
||||||
|
"loss": 2.1989,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.050505050505050504,
|
||||||
|
"grad_norm": 6.8125,
|
||||||
|
"learning_rate": 8.000000000000001e-06,
|
||||||
|
"loss": 2.0533,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06060606060606061,
|
||||||
|
"grad_norm": 5.84375,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"loss": 2.071,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.0707070707070707,
|
||||||
|
"grad_norm": 5.46875,
|
||||||
|
"learning_rate": 9.893617021276596e-06,
|
||||||
|
"loss": 2.0025,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.08080808080808081,
|
||||||
|
"grad_norm": 5.0625,
|
||||||
|
"learning_rate": 9.787234042553192e-06,
|
||||||
|
"loss": 1.7837,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09090909090909091,
|
||||||
|
"grad_norm": 4.5625,
|
||||||
|
"learning_rate": 9.680851063829787e-06,
|
||||||
|
"loss": 1.8194,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10101010101010101,
|
||||||
|
"grad_norm": 4.34375,
|
||||||
|
"learning_rate": 9.574468085106385e-06,
|
||||||
|
"loss": 1.7647,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.10101010101010101,
|
||||||
|
"eval_loss": 1.8501181602478027,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.5153,
|
||||||
|
"eval_samples_per_second": 31.891,
|
||||||
|
"eval_steps_per_second": 15.946,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1111111111111111,
|
||||||
|
"grad_norm": 4.1875,
|
||||||
|
"learning_rate": 9.46808510638298e-06,
|
||||||
|
"loss": 1.7479,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.12121212121212122,
|
||||||
|
"grad_norm": 4.6875,
|
||||||
|
"learning_rate": 9.361702127659576e-06,
|
||||||
|
"loss": 1.9077,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13131313131313133,
|
||||||
|
"grad_norm": 3.984375,
|
||||||
|
"learning_rate": 9.255319148936171e-06,
|
||||||
|
"loss": 1.7011,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1414141414141414,
|
||||||
|
"grad_norm": 3.921875,
|
||||||
|
"learning_rate": 9.148936170212767e-06,
|
||||||
|
"loss": 1.6132,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.15151515151515152,
|
||||||
|
"grad_norm": 3.484375,
|
||||||
|
"learning_rate": 9.042553191489362e-06,
|
||||||
|
"loss": 1.5589,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16161616161616163,
|
||||||
|
"grad_norm": 4.28125,
|
||||||
|
"learning_rate": 8.936170212765958e-06,
|
||||||
|
"loss": 1.7689,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1717171717171717,
|
||||||
|
"grad_norm": 3.90625,
|
||||||
|
"learning_rate": 8.829787234042555e-06,
|
||||||
|
"loss": 1.7021,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18181818181818182,
|
||||||
|
"grad_norm": 3.90625,
|
||||||
|
"learning_rate": 8.72340425531915e-06,
|
||||||
|
"loss": 1.596,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.1919191919191919,
|
||||||
|
"grad_norm": 3.640625,
|
||||||
|
"learning_rate": 8.617021276595746e-06,
|
||||||
|
"loss": 1.5814,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20202020202020202,
|
||||||
|
"grad_norm": 4.3125,
|
||||||
|
"learning_rate": 8.510638297872341e-06,
|
||||||
|
"loss": 1.6297,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20202020202020202,
|
||||||
|
"eval_loss": 1.6177141666412354,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.4588,
|
||||||
|
"eval_samples_per_second": 32.296,
|
||||||
|
"eval_steps_per_second": 16.148,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.21212121212121213,
|
||||||
|
"grad_norm": 5.21875,
|
||||||
|
"learning_rate": 8.404255319148937e-06,
|
||||||
|
"loss": 1.4007,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2222222222222222,
|
||||||
|
"grad_norm": 3.640625,
|
||||||
|
"learning_rate": 8.297872340425532e-06,
|
||||||
|
"loss": 1.5302,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.23232323232323232,
|
||||||
|
"grad_norm": 4.625,
|
||||||
|
"learning_rate": 8.191489361702128e-06,
|
||||||
|
"loss": 1.5728,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24242424242424243,
|
||||||
|
"grad_norm": 4.71875,
|
||||||
|
"learning_rate": 8.085106382978723e-06,
|
||||||
|
"loss": 1.5623,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.25252525252525254,
|
||||||
|
"grad_norm": 4.875,
|
||||||
|
"learning_rate": 7.97872340425532e-06,
|
||||||
|
"loss": 1.6365,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.26262626262626265,
|
||||||
|
"grad_norm": 4.6875,
|
||||||
|
"learning_rate": 7.872340425531916e-06,
|
||||||
|
"loss": 1.5573,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2727272727272727,
|
||||||
|
"grad_norm": 4.5625,
|
||||||
|
"learning_rate": 7.765957446808511e-06,
|
||||||
|
"loss": 1.5593,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2828282828282828,
|
||||||
|
"grad_norm": 4.0625,
|
||||||
|
"learning_rate": 7.659574468085107e-06,
|
||||||
|
"loss": 1.5289,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.29292929292929293,
|
||||||
|
"grad_norm": 4.53125,
|
||||||
|
"learning_rate": 7.553191489361703e-06,
|
||||||
|
"loss": 1.4426,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30303030303030304,
|
||||||
|
"grad_norm": 3.765625,
|
||||||
|
"learning_rate": 7.446808510638298e-06,
|
||||||
|
"loss": 1.5221,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.30303030303030304,
|
||||||
|
"eval_loss": 1.5113080739974976,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.4717,
|
||||||
|
"eval_samples_per_second": 32.202,
|
||||||
|
"eval_steps_per_second": 16.101,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.31313131313131315,
|
||||||
|
"grad_norm": 3.640625,
|
||||||
|
"learning_rate": 7.340425531914894e-06,
|
||||||
|
"loss": 1.399,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32323232323232326,
|
||||||
|
"grad_norm": 4.0625,
|
||||||
|
"learning_rate": 7.234042553191491e-06,
|
||||||
|
"loss": 1.5572,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3333333333333333,
|
||||||
|
"grad_norm": 3.65625,
|
||||||
|
"learning_rate": 7.127659574468085e-06,
|
||||||
|
"loss": 1.3714,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3434343434343434,
|
||||||
|
"grad_norm": 3.890625,
|
||||||
|
"learning_rate": 7.021276595744682e-06,
|
||||||
|
"loss": 1.4515,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.35353535353535354,
|
||||||
|
"grad_norm": 3.640625,
|
||||||
|
"learning_rate": 6.914893617021278e-06,
|
||||||
|
"loss": 1.4222,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36363636363636365,
|
||||||
|
"grad_norm": 3.3125,
|
||||||
|
"learning_rate": 6.808510638297873e-06,
|
||||||
|
"loss": 1.375,
|
||||||
|
"step": 36
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.37373737373737376,
|
||||||
|
"grad_norm": 3.625,
|
||||||
|
"learning_rate": 6.702127659574469e-06,
|
||||||
|
"loss": 1.4592,
|
||||||
|
"step": 37
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3838383838383838,
|
||||||
|
"grad_norm": 3.453125,
|
||||||
|
"learning_rate": 6.595744680851064e-06,
|
||||||
|
"loss": 1.3722,
|
||||||
|
"step": 38
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3939393939393939,
|
||||||
|
"grad_norm": 3.6875,
|
||||||
|
"learning_rate": 6.48936170212766e-06,
|
||||||
|
"loss": 1.4548,
|
||||||
|
"step": 39
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.40404040404040403,
|
||||||
|
"grad_norm": 3.453125,
|
||||||
|
"learning_rate": 6.382978723404256e-06,
|
||||||
|
"loss": 1.5035,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.40404040404040403,
|
||||||
|
"eval_loss": 1.443503499031067,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.5368,
|
||||||
|
"eval_samples_per_second": 31.74,
|
||||||
|
"eval_steps_per_second": 15.87,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.41414141414141414,
|
||||||
|
"grad_norm": 3.1875,
|
||||||
|
"learning_rate": 6.276595744680851e-06,
|
||||||
|
"loss": 1.4053,
|
||||||
|
"step": 41
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.42424242424242425,
|
||||||
|
"grad_norm": 3.453125,
|
||||||
|
"learning_rate": 6.170212765957447e-06,
|
||||||
|
"loss": 1.3533,
|
||||||
|
"step": 42
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.43434343434343436,
|
||||||
|
"grad_norm": 4.09375,
|
||||||
|
"learning_rate": 6.063829787234044e-06,
|
||||||
|
"loss": 1.4969,
|
||||||
|
"step": 43
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4444444444444444,
|
||||||
|
"grad_norm": 3.8125,
|
||||||
|
"learning_rate": 5.957446808510638e-06,
|
||||||
|
"loss": 1.4565,
|
||||||
|
"step": 44
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.45454545454545453,
|
||||||
|
"grad_norm": 4.0,
|
||||||
|
"learning_rate": 5.851063829787235e-06,
|
||||||
|
"loss": 1.389,
|
||||||
|
"step": 45
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.46464646464646464,
|
||||||
|
"grad_norm": 4.625,
|
||||||
|
"learning_rate": 5.744680851063831e-06,
|
||||||
|
"loss": 1.4511,
|
||||||
|
"step": 46
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.47474747474747475,
|
||||||
|
"grad_norm": 3.890625,
|
||||||
|
"learning_rate": 5.638297872340426e-06,
|
||||||
|
"loss": 1.4159,
|
||||||
|
"step": 47
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.48484848484848486,
|
||||||
|
"grad_norm": 3.90625,
|
||||||
|
"learning_rate": 5.531914893617022e-06,
|
||||||
|
"loss": 1.3452,
|
||||||
|
"step": 48
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.494949494949495,
|
||||||
|
"grad_norm": 4.375,
|
||||||
|
"learning_rate": 5.425531914893617e-06,
|
||||||
|
"loss": 1.3517,
|
||||||
|
"step": 49
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5050505050505051,
|
||||||
|
"grad_norm": 3.84375,
|
||||||
|
"learning_rate": 5.319148936170213e-06,
|
||||||
|
"loss": 1.3475,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5050505050505051,
|
||||||
|
"eval_loss": 1.399296522140503,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.4653,
|
||||||
|
"eval_samples_per_second": 32.249,
|
||||||
|
"eval_steps_per_second": 16.124,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5151515151515151,
|
||||||
|
"grad_norm": 3.515625,
|
||||||
|
"learning_rate": 5.212765957446809e-06,
|
||||||
|
"loss": 1.3007,
|
||||||
|
"step": 51
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5252525252525253,
|
||||||
|
"grad_norm": 3.515625,
|
||||||
|
"learning_rate": 5.106382978723404e-06,
|
||||||
|
"loss": 1.3047,
|
||||||
|
"step": 52
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5353535353535354,
|
||||||
|
"grad_norm": 3.734375,
|
||||||
|
"learning_rate": 5e-06,
|
||||||
|
"loss": 1.3374,
|
||||||
|
"step": 53
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5454545454545454,
|
||||||
|
"grad_norm": 3.703125,
|
||||||
|
"learning_rate": 4.893617021276596e-06,
|
||||||
|
"loss": 1.2432,
|
||||||
|
"step": 54
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 4.09375,
|
||||||
|
"learning_rate": 4.787234042553192e-06,
|
||||||
|
"loss": 1.4018,
|
||||||
|
"step": 55
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5656565656565656,
|
||||||
|
"grad_norm": 3.78125,
|
||||||
|
"learning_rate": 4.680851063829788e-06,
|
||||||
|
"loss": 1.4056,
|
||||||
|
"step": 56
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5757575757575758,
|
||||||
|
"grad_norm": 3.5625,
|
||||||
|
"learning_rate": 4.574468085106383e-06,
|
||||||
|
"loss": 1.3512,
|
||||||
|
"step": 57
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5858585858585859,
|
||||||
|
"grad_norm": 3.375,
|
||||||
|
"learning_rate": 4.468085106382979e-06,
|
||||||
|
"loss": 1.3737,
|
||||||
|
"step": 58
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5959595959595959,
|
||||||
|
"grad_norm": 3.5625,
|
||||||
|
"learning_rate": 4.361702127659575e-06,
|
||||||
|
"loss": 1.3453,
|
||||||
|
"step": 59
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6060606060606061,
|
||||||
|
"grad_norm": 3.25,
|
||||||
|
"learning_rate": 4.255319148936171e-06,
|
||||||
|
"loss": 1.3598,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6060606060606061,
|
||||||
|
"eval_loss": 1.3689942359924316,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.891,
|
||||||
|
"eval_samples_per_second": 29.442,
|
||||||
|
"eval_steps_per_second": 14.721,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6161616161616161,
|
||||||
|
"grad_norm": 3.90625,
|
||||||
|
"learning_rate": 4.148936170212766e-06,
|
||||||
|
"loss": 1.4119,
|
||||||
|
"step": 61
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6262626262626263,
|
||||||
|
"grad_norm": 3.734375,
|
||||||
|
"learning_rate": 4.042553191489362e-06,
|
||||||
|
"loss": 1.3028,
|
||||||
|
"step": 62
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6363636363636364,
|
||||||
|
"grad_norm": 3.53125,
|
||||||
|
"learning_rate": 3.936170212765958e-06,
|
||||||
|
"loss": 1.2088,
|
||||||
|
"step": 63
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6464646464646465,
|
||||||
|
"grad_norm": 3.5,
|
||||||
|
"learning_rate": 3.8297872340425535e-06,
|
||||||
|
"loss": 1.3143,
|
||||||
|
"step": 64
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6565656565656566,
|
||||||
|
"grad_norm": 3.65625,
|
||||||
|
"learning_rate": 3.723404255319149e-06,
|
||||||
|
"loss": 1.3123,
|
||||||
|
"step": 65
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6666666666666666,
|
||||||
|
"grad_norm": 4.25,
|
||||||
|
"learning_rate": 3.6170212765957453e-06,
|
||||||
|
"loss": 1.356,
|
||||||
|
"step": 66
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6767676767676768,
|
||||||
|
"grad_norm": 3.796875,
|
||||||
|
"learning_rate": 3.510638297872341e-06,
|
||||||
|
"loss": 1.4043,
|
||||||
|
"step": 67
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6868686868686869,
|
||||||
|
"grad_norm": 3.9375,
|
||||||
|
"learning_rate": 3.4042553191489363e-06,
|
||||||
|
"loss": 1.3052,
|
||||||
|
"step": 68
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.696969696969697,
|
||||||
|
"grad_norm": 3.578125,
|
||||||
|
"learning_rate": 3.297872340425532e-06,
|
||||||
|
"loss": 1.3282,
|
||||||
|
"step": 69
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7070707070707071,
|
||||||
|
"grad_norm": 4.1875,
|
||||||
|
"learning_rate": 3.191489361702128e-06,
|
||||||
|
"loss": 1.4262,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7070707070707071,
|
||||||
|
"eval_loss": 1.3482567071914673,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.9944,
|
||||||
|
"eval_samples_per_second": 28.832,
|
||||||
|
"eval_steps_per_second": 14.416,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7171717171717171,
|
||||||
|
"grad_norm": 3.984375,
|
||||||
|
"learning_rate": 3.0851063829787237e-06,
|
||||||
|
"loss": 1.4252,
|
||||||
|
"step": 71
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7272727272727273,
|
||||||
|
"grad_norm": 4.1875,
|
||||||
|
"learning_rate": 2.978723404255319e-06,
|
||||||
|
"loss": 1.3866,
|
||||||
|
"step": 72
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7373737373737373,
|
||||||
|
"grad_norm": 4.03125,
|
||||||
|
"learning_rate": 2.8723404255319155e-06,
|
||||||
|
"loss": 1.3893,
|
||||||
|
"step": 73
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7474747474747475,
|
||||||
|
"grad_norm": 3.828125,
|
||||||
|
"learning_rate": 2.765957446808511e-06,
|
||||||
|
"loss": 1.3093,
|
||||||
|
"step": 74
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7575757575757576,
|
||||||
|
"grad_norm": 3.6875,
|
||||||
|
"learning_rate": 2.6595744680851065e-06,
|
||||||
|
"loss": 1.2562,
|
||||||
|
"step": 75
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7676767676767676,
|
||||||
|
"grad_norm": 3.8125,
|
||||||
|
"learning_rate": 2.553191489361702e-06,
|
||||||
|
"loss": 1.2896,
|
||||||
|
"step": 76
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7777777777777778,
|
||||||
|
"grad_norm": 3.546875,
|
||||||
|
"learning_rate": 2.446808510638298e-06,
|
||||||
|
"loss": 1.3052,
|
||||||
|
"step": 77
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7878787878787878,
|
||||||
|
"grad_norm": 4.28125,
|
||||||
|
"learning_rate": 2.340425531914894e-06,
|
||||||
|
"loss": 1.2805,
|
||||||
|
"step": 78
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.797979797979798,
|
||||||
|
"grad_norm": 3.796875,
|
||||||
|
"learning_rate": 2.2340425531914894e-06,
|
||||||
|
"loss": 1.2598,
|
||||||
|
"step": 79
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8080808080808081,
|
||||||
|
"grad_norm": 3.734375,
|
||||||
|
"learning_rate": 2.1276595744680853e-06,
|
||||||
|
"loss": 1.3316,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8080808080808081,
|
||||||
|
"eval_loss": 1.3349997997283936,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.7579,
|
||||||
|
"eval_samples_per_second": 30.265,
|
||||||
|
"eval_steps_per_second": 15.133,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8181818181818182,
|
||||||
|
"grad_norm": 3.578125,
|
||||||
|
"learning_rate": 2.021276595744681e-06,
|
||||||
|
"loss": 1.2956,
|
||||||
|
"step": 81
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8282828282828283,
|
||||||
|
"grad_norm": 3.53125,
|
||||||
|
"learning_rate": 1.9148936170212767e-06,
|
||||||
|
"loss": 1.317,
|
||||||
|
"step": 82
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8383838383838383,
|
||||||
|
"grad_norm": 3.71875,
|
||||||
|
"learning_rate": 1.8085106382978727e-06,
|
||||||
|
"loss": 1.2709,
|
||||||
|
"step": 83
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8484848484848485,
|
||||||
|
"grad_norm": 3.5625,
|
||||||
|
"learning_rate": 1.7021276595744682e-06,
|
||||||
|
"loss": 1.3115,
|
||||||
|
"step": 84
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8585858585858586,
|
||||||
|
"grad_norm": 3.796875,
|
||||||
|
"learning_rate": 1.595744680851064e-06,
|
||||||
|
"loss": 1.3131,
|
||||||
|
"step": 85
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8686868686868687,
|
||||||
|
"grad_norm": 3.375,
|
||||||
|
"learning_rate": 1.4893617021276596e-06,
|
||||||
|
"loss": 1.2993,
|
||||||
|
"step": 86
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8787878787878788,
|
||||||
|
"grad_norm": 3.828125,
|
||||||
|
"learning_rate": 1.3829787234042555e-06,
|
||||||
|
"loss": 1.2934,
|
||||||
|
"step": 87
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8888888888888888,
|
||||||
|
"grad_norm": 3.890625,
|
||||||
|
"learning_rate": 1.276595744680851e-06,
|
||||||
|
"loss": 1.3148,
|
||||||
|
"step": 88
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.898989898989899,
|
||||||
|
"grad_norm": 4.125,
|
||||||
|
"learning_rate": 1.170212765957447e-06,
|
||||||
|
"loss": 1.4243,
|
||||||
|
"step": 89
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9090909090909091,
|
||||||
|
"grad_norm": 3.53125,
|
||||||
|
"learning_rate": 1.0638297872340427e-06,
|
||||||
|
"loss": 1.2164,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9090909090909091,
|
||||||
|
"eval_loss": 1.3271279335021973,
|
||||||
|
"eval_model_preparation_time": 0.0192,
|
||||||
|
"eval_runtime": 4.7066,
|
||||||
|
"eval_samples_per_second": 30.595,
|
||||||
|
"eval_steps_per_second": 15.298,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9191919191919192,
|
||||||
|
"grad_norm": 4.125,
|
||||||
|
"learning_rate": 9.574468085106384e-07,
|
||||||
|
"loss": 1.4069,
|
||||||
|
"step": 91
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9292929292929293,
|
||||||
|
"grad_norm": 3.921875,
|
||||||
|
"learning_rate": 8.510638297872341e-07,
|
||||||
|
"loss": 1.3035,
|
||||||
|
"step": 92
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9393939393939394,
|
||||||
|
"grad_norm": 3.75,
|
||||||
|
"learning_rate": 7.446808510638298e-07,
|
||||||
|
"loss": 1.2968,
|
||||||
|
"step": 93
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9494949494949495,
|
||||||
|
"grad_norm": 3.609375,
|
||||||
|
"learning_rate": 6.382978723404255e-07,
|
||||||
|
"loss": 1.3289,
|
||||||
|
"step": 94
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9595959595959596,
|
||||||
|
"grad_norm": 3.78125,
|
||||||
|
"learning_rate": 5.319148936170213e-07,
|
||||||
|
"loss": 1.3311,
|
||||||
|
"step": 95
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9696969696969697,
|
||||||
|
"grad_norm": 3.75,
|
||||||
|
"learning_rate": 4.2553191489361704e-07,
|
||||||
|
"loss": 1.3339,
|
||||||
|
"step": 96
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9797979797979798,
|
||||||
|
"grad_norm": 3.796875,
|
||||||
|
"learning_rate": 3.1914893617021275e-07,
|
||||||
|
"loss": 1.3035,
|
||||||
|
"step": 97
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.98989898989899,
|
||||||
|
"grad_norm": 3.3125,
|
||||||
|
"learning_rate": 2.1276595744680852e-07,
|
||||||
|
"loss": 1.2145,
|
||||||
|
"step": 98
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 3.640625,
|
||||||
|
"learning_rate": 1.0638297872340426e-07,
|
||||||
|
"loss": 1.2494,
|
||||||
|
"step": 99
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 99,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 5000,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.698740109213696e+16,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
checkpoint-99/training_args.bin
Normal file
3
checkpoint-99/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a6fc2d3ecda99b84007c5d8ca2fe15988d1fb4663ddd156f91da972bb8803faa
|
||||||
|
size 6097
|
||||||
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": 128000,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"eos_token_id": 128009,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 128004,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": {
|
||||||
|
"factor": 8.0,
|
||||||
|
"high_freq_factor": 4.0,
|
||||||
|
"low_freq_factor": 1.0,
|
||||||
|
"original_max_position_embeddings": 8192,
|
||||||
|
"rope_type": "llama3"
|
||||||
|
},
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.56.2",
|
||||||
|
"unsloth_fixed": true,
|
||||||
|
"unsloth_version": "2025.10.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 128256
|
||||||
|
}
|
||||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b5bd03167a5f2dd3be8ae1fdf83176a4d9a979ddc321d7e101b759dc88fa3c0b
|
||||||
|
size 4976698672
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8b8f5664d817a95ed266d167898a75fe185025f2d5c6f534699527f8c3c193c1
|
||||||
|
size 4999802720
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ff4de55d69ede141ba2f92e7dc903885e3961c318f11fbfc9907c99a815c9520
|
||||||
|
size 4915916176
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0a0bc49dfb4eea8f7189939782440906830c7abf6e73c4468bcbbec7c7438586
|
||||||
|
size 1168138808
|
||||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16060522496
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-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.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.weight": "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.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.weight": "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-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-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.weight": "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-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|finetune_right_pad_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2067
tokenizer_config.json
Normal file
2067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user