Eden's-Fall-L3.3-70b-0.3b

Storytelling and RP model. 3/3 stage merge.

Final stage of a 3 part merge. I wanted to try to create a model for creative writing that had lengthy responses without repeating story beats. This one feels relatively unique, but still being tested.

This is still a work in progress unless Meta (or Mistral 👉👈) finally releases a decent model. Any feedback would be appreciated.

Static quants - https://huggingface.co/mradermacher/Edens-Fall-L3.3-70b-0.3b-GGUF

imatrix quants - https://huggingface.co/mradermacher/Edens-Fall-L3.3-70b-0.3b-i1-GGUF

Sampler Settings to start with:

Temp: 0.95 - 1

Min P: 0.015 - 0.02

Top P: 0.97 - 1

Merge Details

Merge Method

This model was merged using the Multi-SLERP merge method.

Models Merged

The following models were included in the merge:

• BruhzWater/Serpents-Tongue-L3.3-70b-0.3
• BruhzWater/Apocrypha-L3.3-70b-0.3
• BruhzWater/Liliths-Whisper-L3.3-70b-0.1

BruhzWater/Serpents-Tongue-L3.3-70b-0.3

• TheDrummer--Anubis-70B-v1.1 (super duper detail sauce)
• TheDrummer--Fallen-Llama-3.3-70B-v1 (big bad mean sauce)
• Ppoyaa--MythoNemo-L3.1-70B-v1.0 (ultra mega writing sauce)
• Sao10K--L3.1-70B-Hanami-x1 (turbo deluxe smut sauce)
• Sao10K--70B-L3.3-mhnnn-x1 (giga max ??? sauce)

Liliths-Whisper-L3.3-70b-0.1

• Sao10K--70B-L3.3-Cirrus-x1 (grand supreme balance sauce)
• ArliAI--Llama-3.3-70B-ArliAI-RPMax-v2 (ultimate nextlevel rp sauce)
• Sao10K--L3.3-70B-Euryale-v2.3 (hyper beam creative sauce xD)
• ReadyArt--L3.3-The-Omega-Directive-70B-Unslop-v2.0 (optimal elite nono sauce)
• TheDrummer--Fallen-Llama-3.3-70B-v1 (big bad mean sauce)

Apocrypha-L3.3-70b-0.3

• nbeerbower--Llama3.1-Gutenberg-Doppel-70B (extra ancient book sauce)
• Doctor-Shotgun--L3.3-70B-Magnum-Diamond (divine horny prose sauce)
• TheDrummer--Fallen-Llama-3.3-70B-v1 (big bad mean sauce)
• tdrussell--Llama-3-70B-Instruct-Storywriter (uber premium story sauce)
• EVA-UNIT-01--EVA-LLaMA-3.33-70B-v0.0 (unrivaled epic narrative sauce)

Eden-L3.3-70b-0.3 (base)

• deepcogito--cogito-v1-preview-llama-70B (base)
• nvidia--Llama-3.1-Nemotron-70B-Instruct-HF
• Delta-Vector--Austral-70B-Winton
• watt-ai--watt-tool-70B
• zerofata--L3.3-GeneticLemonade-Unleashed-v3-70B
• marcelbinz--Llama-3.1-Centaur-70B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: BruhzWater/Liliths-Whisper-L3.3-70b-0.1
    parameters:
      weight: [0.2]
  - model: BruhzWater/Apocrypha-L3.3-70b-0.3
    parameters:
      weight: [0.2]
  - model: BruhzWater/Serpents-Tongue-L3.3-70b-0.3
    parameters:
      weight: [0.6]
merge_method: multislerp
tokenizer:
  source: /workspace/cache/models--bruhzair--prototype-0.4x257/snapshots/60a848fe9776f453b6f640662ca07493da8c1d12
chat_template: llama3
parameters:
  normalize_weights: false
  eps: 1e-8
pad_to_multiple_of: 8
int8_mask: true
dtype: bfloat16

Chat template:

• Llama3

Instruct Template:

• Llama3

• Deep Cogito - https://huggingface.co/deepcogito/cogito-v1-preview-llama-70B

{{- '<|begin_of_text|>' }}
{%- if not tools is defined %}
    {%- set tools = none %}
{%- endif %}
{%- if not enable_thinking is defined %}
    {%- set enable_thinking = false %}
{%- 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 %}
{#- Set the system message. If enable_thinking is true, add the "Enable deep thinking subroutine." #}
{%- if enable_thinking %}
    {%- if system_message != "" %}
        {%- set system_message = "Enable deep thinking subroutine.

" ~ system_message %}
    {%- else %}
        {%- set system_message = "Enable deep thinking subroutine." %}
    {%- endif %}
{%- endif %}
{#- Set the system message. In case there are tools present, add them to the system message. #}
{%- if tools is not none or system_message != '' %}
    {{- "<|start_header_id|>system<|end_header_id|>

" }}
    {{- system_message }}
    {%- if tools is not none %}
        {%- if system_message != "" %}
            {{- "

" }}
        {%- endif %}
        {{- "Available Tools:
" }}
        {%- for t in tools %}
            {{- t | tojson(indent=4) }}
            {{- "

" }}
        {%- endfor %}
    {%- endif %}
    {{- "<|eot_id|>" }}
{%- endif %}

{#- Rest of the messages #}
{%- for message in messages %}
    {#- The special cases are when the message is from a tool (via role ipython/tool/tool_results) or when the message is from the assistant, but has "tool_calls". If not, we add the message directly as usual. #}
    {#- Case 1 - Usual, non tool related message. #}
    {%- if not (message.role == "ipython" or message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>

' }}
        {%- if message['content'] is string %}
            {{- message['content'] | trim }}
        {%- else %}
            {%- for item in message['content'] %}
                {%- if item.type == 'text' %}
                    {{- item.text | trim }}
                {%- endif %}
            {%- endfor %}
        {%- endif %}
        {{- '<|eot_id|>' }}

    {#- Case 2 - the response is from the assistant, but has a tool call returned. The assistant may also have returned some content along with the tool call. #}
    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
        {{- "<|start_header_id|>assistant<|end_header_id|>

" }}
        {%- if message['content'] is string %}
            {{- message['content'] | trim }}
        {%- else %}
            {%- for item in message['content'] %}
                {%- if item.type == 'text' %}
                    {{- item.text | trim }}
                    {%- if item.text | trim != "" %}
                        {{- "

" }}
                    {%- endif %}
                {%- endif %}
            {%- endfor %}
        {%- endif %}
        {{- "[" }}
        {%- for tool_call in message.tool_calls %}
            {%- set out = tool_call.function|tojson %}
            {%- if not tool_call.id is defined %}
                {{- out }}
            {%- else %}
                {{- out[:-1] }}
                {{- ', "id": "' + tool_call.id + '"}' }}
            {%- endif %}
            {%- if not loop.last %}
                {{- ", " }}
            {%- else %}
                {{- "]<|eot_id|>" }}
            {%- endif %}
        {%- endfor %}

    {#- Case 3 - the response is from a tool call. The tool call may have an id associated with it as well. If it does, we add it to the prompt. #}
    {%- elif message.role == "ipython" or message["role"] == "tool_results" or message["role"] == "tool" %}
        {{- "<|start_header_id|>ipython<|end_header_id|>

" }}
        {%- if message.tool_call_id is defined and message.tool_call_id != '' %}
            {{- '{"content": ' + (message.content | tojson) + ', "call_id": "' + message.tool_call_id + '"}' }}
        {%- else %}
            {{- '{"content": ' + (message.content | tojson) + '}' }}
        {%- endif %}
        {{- "<|eot_id|>" }}
    {%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
    {{- '<|start_header_id|>assistant<|end_header_id|>

' }}
{%- endif %}