DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k
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: DavidAU/Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-24 22:19:24 +08:00
commit 17e0cbf60f
14 changed files with 2883 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.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
matrix-neo-reloaded-fight.gif filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

297
README.md Normal file
View File

@@ -0,0 +1,297 @@
---
license: apache-2.0
datasets:
- TeichAI/gemini-2.5-flash-11000x
base_model:
- allura-forge/Llama-3.3-8B-Instruct
language:
- en
- fr
- de
- es
- it
- pt
- zh
- ja
- ru
- ko
tags:
- thinking
- reasoning
- Gemini Flash
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- fiction writing
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prosing
- vivid writing
- fiction
- roleplaying
- bfloat16
- role play
- 128k context
- llama3.3
- llama-3
- llama-3.3
- unsloth
- finetune
pipeline_tag: text-generation
library_name: transformers
---
<H2>Llama-3.3-8B-Thinking-Gemini-Flash-11000x-128k</H2>
<img src="matrix-neo-reloaded-fight.gif" style="float:right; width:300px; height:300px; padding:10px;">
What madness is this?
Someone found "Llama3.3-8B" source (never publicly released) in the "wild", then it was adjusted back to 128k and then
I added my own special madness by training the model with Unsloth (3 epochs) and Gemini-2.5-flash-11000x (11000 samples) dataset.
This has created an Thinking model (128k context, Llama 3.3 model) which REASONS / THINKS like Gemini, but in a Llama 3.3 8B model.
Note this tuning was not only to create an thinking model, but ALSO update some the model's core knowledge / root training.
1 example generation at the bottom of this page.
Some "Llama" issues may still exist including out-of-date data.
<B>Thinking (will activate automatically) prompts - examples: </B>
Explain orbital mechanics including detailed math and examples.
Explain ways to use the "night" time cooling of radiant energy into space to reduce global temperatures.
Think Deeply: Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800-1000 words.
Think deeply: Tell me a horror story.
[sometimes you don't need the "think deeply"]
EXTENDED:
Come up with a plan to write:
Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800-1000 words.
[ you may need to add after the "plan" appears: "Use the outline now, to write the scene"]
Certain phrases/words will automatically activate thinking:
- explain
- come up with a plan to...
- write a ...
- think about this and come up with a plan.
<B>Instruct (thinking may NOT activate) prompts - examples:</B>
Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear to further the reader's emotional connection to them. 800-1000 words.
Tell me a horror story.
<B>SETTINGS (suggested):</B>
Temp .7, rep pen 1.05, topp: .95, minp .05, topk: 40
Min context window: 4k, but suggest 8k+.
NO system prompt [thinking tags will self generate in MOST cases].
NOTE:
Temp can range from .1 to 2.5 or higher. Temp will NOT affect "thinking activation" in most cases.
Strongly suggest Q4KS or higher // IQ3_M (Imatrix) or higher to avoid reasoning/reasoning activation issues.
SYSTEM PROMPT to "force" thinking (can lead to odd / interesting "output"):
```
A user will ask you to solve a task. You should first draft your thinking process (inner monologue) until you have derived the final answer. Afterwards, write a self-contained summary of your thoughts (i.e. your summary should be succinct but contain all the critical steps you needed to reach the conclusion). You should use Markdown and Latex to format your response. Write both your thoughts and summary in the same language as the task posed by the user.
Your thinking process must follow the template below:
<think>
Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate a correct answer.
</think>
```
---
Special thanks to:
---
https://huggingface.co/allura-forge/Llama-3.3-8B-Instruct
(found the model!)
https://huggingface.co/shb777/Llama-3.3-8B-Instruct-128K
(adjusted to 128k, and other fixes)
https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x
(for the F..ing amazing dataset)
and Unsloth for making tuning too easy:
https://github.com/unslothai/unsloth
Details on the "madness":
https://www.reddit.com/r/LocalLLaMA/comments/1pz7bmv/llama338binstruct/
https://www.reddit.com/r/LocalLLaMA/comments/1q06ddc/update_on_the_llama_33_8b_situation/
---
<B>Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:</B>
In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ;
Set the "Smoothing_factor" to 1.5
: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F"
: in text-generation-webui -> parameters -> lower right.
: In Silly Tavern this is called: "Smoothing"
NOTE: For "text-generation-webui"
-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model)
Source versions (and config files) of my models are here:
https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be
OTHER OPTIONS:
- Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor")
- If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted.
<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
This a "Class 1" model:
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
---
Example: Q4KS , Lmstudio, "suggested settings"
NOTE: Some loss of formatting.
---
<B>
Explain ways to use the "night" time cooling of radiant energy into space to reduce global temperatures.
</B>
[[[thinking start]]]
Analyzing Cooling Mechanisms
I'm currently focused on how we can leverage the natural cooling of radiant energy during nighttime hours. My goal is to identify practical methods for enhancing this process to mitigate global warming. I'm exploring specific techniques and strategies.
Evaluating Radiative Cooling Methods
Now, I'm digging into how different materials and surfaces can be used to enhance radiative cooling. I'm taking a close look at the spectral properties of various materials, especially their emissivity in infrared wavelengths. The goal is to find the best ways to maximize heat loss during nighttime hours.
Synthesizing Practical Applications
I've just finished a thorough brainstorming session on practical applications. I'm now prioritizing strategies that are most impactful, like large-scale urban planning. I'm focusing on how to integrate reflective surfaces and high-emissivity materials into existing infrastructure to maximize the cooling effect during nighttime hours. The ultimate goal is to devise actionable steps.
Prioritizing Strategic Implementation
I've been drilling down further into the specifics of implementation, particularly the "how." I am now considering the feasibility of each strategy, keeping in mind factors like cost, technology availability, and potential for widespread adoption. My focus is on creating a clear, actionable roadmap.
Developing an Actionable Roadmap
The work continues to center around building out a practical implementation guide. Currently, I'm focusing on refining the "how" behind each strategy, with a strong emphasis on feasibility. I am also exploring the potential for integrating multiple strategies into cohesive solutions, ensuring that they complement each other effectively.
Developing the Comprehensive Plan
I'm now deep in the process of building out the comprehensive plan. My focus is still on the practical side, specifically how to translate theoretical concepts into actionable steps. I've broken down my thoughts into distinct sections: surface design, urban planning, and global-scale strategies. I am refining each section, focusing on clarity and feasibility.
[[[thinking end]]]
OUTPUT:
The "night time cooling of radiant energy into space" is a natural process where the Earth's surface radiates heat back out into the vastness of space, primarily in the infrared (IR) spectrum. This process is essential for regulating Earth's temperature, but it is naturally more efficient during the night due to several factors:
- Less Atmospheric Absorption: During the day, a significant portion of outgoing IR radiation is absorbed by greenhouse gases in the atmosphere (like CO2 and water vapor), preventing it from escaping to space. At night, there's less thermal energy generated by the sun to be absorbed, leading to less overall atmospheric absorption.
- Higher Temperature Gradient: The surface temperature drops significantly overnight while the outer atmosphere remains relatively cold, creating a stronger temperature gradient for heat loss.
To leverage this natural process and reduce global temperatures, strategies often revolve around enhancing the Earth's ability to radiate heat more efficiently into space, especially during the cooler nighttime hours. While "night time cooling" isn't a direct cause of temperature reduction (it's a natural phenomenon itself), strategies that enhance the efficacy of this natural process contribute to it.
Here are ways to use and enhance this natural cooling mechanism:
1. Surface Design & Materials (Local & Regional)
The most straightforward way to enhance radiative cooling is by designing surfaces and buildings that emit infrared radiation more efficiently than standard materials.
- High Emissivity Materials: Using materials with very high emissivity (close to 1) in the IR spectrum, especially in the 8-14 µm range. Examples include:
- White/Albedo Coatings: High-albedo (reflective) surfaces are often used in conjunction with high emissivity. While the white reflects visible light and absorbs less solar radiation, it also provides a large surface area for IR emission.
- Specialized Coatings/Paints: Some coatings can be engineered to have extremely high IR emissivity while also being durable and aesthetically pleasing.
- Optical Brighteners (OBs): Incorporating specific optical brighteners into building materials (e.g., concrete, paint) can dramatically increase IR emissivity without changing visible color.
Structural Designs:
- Cooling Facades: Designing building facades with specific geometric shapes or materials that create "cold spots" by reflecting sunlight and emitting IR radiation more effectively than the surrounding environment.
- Dome-Shaped Structures: A dome shape allows sunlight to be reflected upwards and outwards, while the underside of the dome is exposed to a relatively cooler sky for radiative emission.
- Passive Radiative Cooling Systems: These systems often involve a network of "cooling panels" or "evaporative cooling towers" that are designed to radiate heat downwards towards a reflective surface (like water or a highly reflective material) and then outwards into the sky.
- Cooling Tiles/Pavers: Using specialized pavers that absorb and store heat during the day, then radiate it out to the sky at night.
2. Urban Planning & Green Infrastructure (Regional)
Cities are massive heat sinks, and their surfaces often have high thermal emissivity due to dark materials like asphalt and concrete.
- Green Roofs & Walls: Covering rooftops and walls with vegetation significantly reduces surface temperature, acting as a "cool sponge." This lower surface temperature then radiates less energy into the atmosphere during the day but also means there's more efficient cooling available at night.
- Albedo-Enhancing Pavement: Using lighter-colored asphalt or concrete for roads and sidewalks can reflect more solar radiation and also contribute to IR emission.
- Reflective Surfaces: Incorporating large areas of highly reflective surfaces (e.g., polished stainless steel, white glass) into urban environments can not only reflect sunlight but also provide a larger surface area for IR emission at night.
- Water Features: Incorporating large bodies of water (lakes, reservoirs, even extensive fountains) into urban landscapes is highly effective. Water has a very high IR emissivity and can absorb and release heat slowly, helping to cool the surrounding air through evaporation and direct radiative transfer.
3. Agricultural Practices (Global)
Agricultural land surfaces represent a significant portion of the Earth's surface.
- Lighter Crop Strips: Interspersing strips of lighter-colored crops or reflective mulch among darker plants can increase the overall albedo of agricultural fields, reflecting more sunlight and allowing for greater nighttime radiative cooling from the entire area.
- Optical Brightener Mulch: Similar to OBs in materials, specialized optical brighteners can be incorporated into mulch or irrigation water to increase the IR emissivity of soil surfaces.
- Reduced Tillage Practices: Minimizing disturbance to soil can reduce its thermal conductivity and increase its surface temperature at night, allowing for more efficient radiative cooling.
4. Global Atmospheric Modification (Highly Experimental & Ethical Considerations)
These are very large-scale, highly complex, and often ethically contentious strategies that aim to change the atmospheric properties to allow for greater radiative cooling.
- Stratospheric Aerosol Injection (SAI): Injecting small particles into the stratosphere to increase solar radiation scattering back into space. While primarily a solar radiation management (SRM) technique, SAI can indirectly enhance nighttime radiative cooling by reducing the overall atmospheric temperature and thus the "backradiation" that opposes surface cooling.
- Atmospheric Ionic Manipulation/Cloud Seeding: Some theoretical ideas suggest manipulating the ion composition of the atmosphere or cloud formation to make clouds more reflective or to create persistent cirrus clouds (which reflect more sunlight and have higher IR emissivity) over land. However, these are highly speculative and carry significant unknown risks.
5. Space-Based Reflectors (Hypothetical)
While not directly "night time cooling," a hypothetical array of large space-based reflectors could potentially increase the Earth's overall albedo by reflecting more solar radiation back into space, thereby preventing it from warming the atmosphere and the surface in the first place. This would indirectly lead to a greater ability for the Earth to radiatively cool at night, as there would be less excess heat generated during the day.
Key Considerations & Challenges:
- Spectral Matching: Ensuring that the materials used emit IR radiation effectively within the atmospheric windows where there is minimal absorption.
- Atmospheric Dynamics: The effectiveness of radiative cooling can be affected by wind patterns (dissipating boundary layers), humidity, and even aerosols.
- Economics & Implementation: Many of these methods require significant investment in research, development, and deployment. Scaling up from local experiments to global impact is a major hurdle.
- Ethical & Governance Issues: Large-scale geoengineering projects, especially those with atmospheric or solar modification, raise complex ethical questions about responsibility, potential unintended consequences, and international agreements.
- Complementary Strategies: Radiative cooling often works best in conjunction with other climate change mitigation strategies (e.g., reducing greenhouse gas emissions, increasing energy efficiency) rather than as a standalone solution.
In summary, leveraging the "night time cooling of radiant energy into space" involves designing surfaces and landscapes to radiate heat more efficiently into the vast IR sink of space, especially during the nighttime hours when atmospheric absorption is less of an issue. This can be achieved through material science innovations, urban planning, and even large-scale agricultural practices, always keeping in mind the complex interplay with Earth's atmosphere and the ethical implications of global climate engineering.

105
chat_template.jinja Normal file
View File

@@ -0,0 +1,105 @@
{{- 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 = "30 Dec 2025" %}
{%- 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 %}

36
config.json Normal file
View File

@@ -0,0 +1,36 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"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,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_theta": 500000.0,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"transformers_version": "5.0.0.dev0",
"use_cache": true,
"vocab_size": 128256
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"max_length": 131072,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "5.0.0.dev0"
}

3
matrix-neo-reloaded-fight.gif Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ce6a53540ca225ace5ff10164b18bbd2ec4172c28abc400c3eb1cdd13fc52eb
size 3506911

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb7b68d8163bb09736899296f5b98abbd5967c7ea9838987996b21ad7ef38b2f
size 4976698672

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d8ca71203c8f14c821cc30984b273ac0e251c5855a9f7bdfccc4b5e2bfba77e2
size 4999802720

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c34666162f67b51d122a3ce99c1b89df3b7cb84fd582acd7c7d36dd6130618fb
size 4915916176

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0680cca0557d7813e2b91b61252d8db0f286c2611761ce0e1fbf31f769d9b0a2
size 1168138808

299
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,299 @@
{
"metadata": {
"total_parameters": 8030261248,
"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"
}
}

16
special_tokens_map.json Normal file
View File

@@ -0,0 +1,16 @@
{
"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
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
size 17209961

2062
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff