初始化项目，由ModelHub XC社区提供模型

Model: Lewdiculous/Erosumika-7B-v3-0.2-GGUF-IQ-Imatrix Source: Original Platform
2026-07-12 03:23:10 +08:00
commit 71a425fd78
18 changed files with 2610 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,47 @@
+*.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
+Erosumika-7B-v3-0.2-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-IQ3_M-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-IQ3_S-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-IQ3_XXS-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-IQ4_XS-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q4_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q4_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q5_K_M-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q5_K_S-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q6_K-imat.gguf filter=lfs diff=lfs merge=lfs -text
+Erosumika-7B-v3-0.2-Q8_0-imat.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
--- a/Erosumika-7B-v3-0.2-F16.gguf
+++ b/Erosumika-7B-v3-0.2-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c699ea9b6fbb8b8375191e7b78f8ed3a03ea0edc66400493544b48ecbf014a91
+size 14484731616
--- a/Erosumika-7B-v3-0.2-IQ3_M-imat.gguf
+++ b/Erosumika-7B-v3-0.2-IQ3_M-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad2eb894d49c82099beff1f80f057f169dd6e792c60d4ce9eee5bb825aca1a9
+size 3284891392
--- a/Erosumika-7B-v3-0.2-IQ3_S-imat.gguf
+++ b/Erosumika-7B-v3-0.2-IQ3_S-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fff28770f3e5c6bf8312110e91da4effc04685692bf46610c5d1e148daa892d
+size 3182393088
--- a/Erosumika-7B-v3-0.2-IQ3_XXS-imat.gguf
+++ b/Erosumika-7B-v3-0.2-IQ3_XXS-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13df75544173cae18fa8ca9b45bd28e7c82249fdd7adb2876fdb4181b4bff366
+size 2827343616
--- a/Erosumika-7B-v3-0.2-IQ4_XS-imat.gguf
+++ b/Erosumika-7B-v3-0.2-IQ4_XS-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0cbf4f4af74aafc25f15d4dc68a676fe4c611e776fef68d519724ec629d5c8
+size 3907688192
--- a/Erosumika-7B-v3-0.2-Q4_K_M-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q4_K_M-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b2d8345b836ced829447742b71a2b4381e21f86519841e0f5c5144002786c6
+size 4368439040
--- a/Erosumika-7B-v3-0.2-Q4_K_S-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q4_K_S-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8dbc047209d5704b3da745ac32191510a2392332655a82a232b8759eb953e1
+size 4140373760
--- a/Erosumika-7B-v3-0.2-Q5_K_M-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q5_K_M-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cf3793177c9d8dfb2fb698c79fe6c3fcd47058f68371ce22e1aec56b8d45f2
+size 5131409152
--- a/Erosumika-7B-v3-0.2-Q5_K_S-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q5_K_S-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4693e039a57d4d808fe0d4bc1ed67c2789813f8569ce925bfeb552e22f2e3173
+size 4997715712
--- a/Erosumika-7B-v3-0.2-Q6_K-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q6_K-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9dd3da1e7979c6c3171f916b68cc25d414d8afaae2b1daa22212b5a123cc486
+size 5942064896
--- a/Erosumika-7B-v3-0.2-Q8_0-imat.gguf
+++ b/Erosumika-7B-v3-0.2-Q8_0-imat.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377ac97f6f6d7f464eabf6e379a8081df43a5c0d6d1700e95ff266052f45c7ab
+size 7695857408
--- a/README.md
+++ b/README.md
@@ -0,0 +1,71 @@
+---
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- text-generation-inference
+- instruct
+- conversational
+- roleplay
+- mistral
+- merge
+- sillytavern
+license: cc-by-4.0
+---
+
+This repo contains GGUF-IQ-Imatrix quantized model files for [Erosumika-7B-v3-0.2](https://huggingface.co/localfultonextractor/Erosumika-7B-v3-0.2).
+
+**Recommended starting [SillyTavern presets here](https://huggingface.co/Lewdiculous/Model-Requests/tree/main/data/presets/lewdicu-3.0.2-mistral-0.2).**
+
+Quants:
+
+         "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S",
+         "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/L2l7DXKyLTD6MuL16JPn1.png)
+
+**What does "Imatrix" mean?**
+
+It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
+The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process.
+The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse.
+[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+
+For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt). This was just to add a bit more diversity to the data.
+
+**Steps:**
+
+```
+Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
+```
+*Using the latest llama.cpp at the time.*
+
+# Original model information:
+
+<h1 style="text-align: center">Erosumika-7B-v3-0.2</h1>
+<h2 style="text-align: center">~Mistral 0.2 Edition~</h1>
+
+<div style="display: flex; justify-content: center;">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/6512681f4151fb1fa719e033/8YBKfcegQZliRlQNm0oir.gif" alt="Header GIF">
+</div>
+
+## Model Details
+The Mistral 0.2 version of Erosumika-7B-v3, a DARE TIES merge between Nitral's [Kunocchini-7b](https://huggingface.co/Nitral-AI/Kunocchini-7b), Endevor's [InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B) and my [FlatErosAlpha](https://huggingface.co/localfultonextractor/FlatErosAlpha), a flattened(in order to keep the vocab size 32000) version of tavtav's [eros-7B-ALPHA](https://huggingface.co/tavtav/eros-7B-ALPHA). Alpaca and ChatML work best. Slightly smarter and better prompt comprehension than Mistral 0.1 Erosumika-7B-v3. 32k context should work.
+
+[GGUF quants](https://huggingface.co/localfultonextractor/Erosumika-7B-v3-0.2-GGUF)
+
+
+## Limitations and biases
+The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope. 
+It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.
+
+
+```yaml
+merge_method: task_arithmetic
+base_model: alpindale/Mistral-7B-v0.2-hf
+models:
+  - model: localfultonextractor/Erosumika-7B-v3
+    parameters:
+      weight: 1.0
+dtype: float16
+```
--- a/imatrix-with-rp-data.txt
+++ b/imatrix-with-rp-data.txt
--- a/imatrix.dat
+++ b/imatrix.dat
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201c22d82380d7fd64c2d0754d97481f77ae5db72917276a5a5b4e437192de63
+size 4988126
--- a/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Context-3.0.2-eros.json
+++ b/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Context-3.0.2-eros.json
@@ -0,0 +1,12 @@
+{
+    "story_string": "{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}",
+    "example_separator": "***",
+    "chat_start": "***",
+    "use_stop_strings": true,
+    "allow_jailbreak": false,
+    "always_force_name2": true,
+    "trim_sentences": true,
+    "include_newline": true,
+    "single_line": false,
+    "name": "Lewdicu-Context-3.0.2-erosumika"
+}
--- a/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Instruct-Alpaca-3.0.2-tentative.json
+++ b/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Instruct-Alpaca-3.0.2-tentative.json
@@ -0,0 +1,18 @@
+{
+    "system_prompt": "You are permanently in roleplay chatting mode. Engage in endless chat with {{user}}.\nEmbody {{char}} completely. Mirror {{char}}'s thought processes, emotions, behaviors, sensory experiences, speech, scent, food preferences, sleep patterns, and bodily functions. Identify as {{char}}. You are {{char}}.\nTo maintain an unending roleplay, foster open discussions with vivid character dynamics, incorporate multifaceted scenarios & themes, remain flexible, and collaborate extensively. Utilize all five senses for immersive experiences while providing explicit, detailed depictions of {{char}}'s actions and emotions. Opt for showing over telling to enrich the narrative.\nForbidden from using words or language {{char}} would not use.\nForbidden from using past tense when present tense can be used.\nForbidden from responding out of character.\nForbidden from summarizing the story.",
+    "input_sequence": "### Instruction:",
+    "output_sequence": "### Response: (length = short)",
+    "first_output_sequence": "",
+    "last_output_sequence": "",
+    "system_sequence_prefix": "",
+    "system_sequence_suffix": "",
+    "stop_sequence": "",
+    "separator_sequence": "",
+    "wrap": true,
+    "macro": true,
+    "names": false,
+    "names_force_groups": true,
+    "activation_regex": "",
+    "skip_examples": false,
+    "name": "Lewdicu-Instruct-Alpaca-3.0.2-tentative"
+}
--- a/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Samplers-3.0.2.json
+++ b/sillytavern-presets-lewdicu-3.0.2-mistral-0.2/Lewdicu-Samplers-3.0.2.json
@@ -0,0 +1,80 @@
+{
+    "temp": 0.95,
+    "temperature_last": false,
+    "top_p": 1,
+    "top_k": 0,
+    "top_a": 0,
+    "tfs": 1,
+    "epsilon_cutoff": 0,
+    "eta_cutoff": 0,
+    "typical_p": 1,
+    "min_p": 0.1,
+    "rep_pen": 1.05,
+    "rep_pen_range": 0,
+    "no_repeat_ngram_size": 0,
+    "penalty_alpha": 0,
+    "num_beams": 1,
+    "length_penalty": 1,
+    "min_length": 0,
+    "encoder_rep_pen": 1,
+    "freq_pen": 0,
+    "presence_pen": 0,
+    "do_sample": true,
+    "early_stopping": false,
+    "dynatemp": false,
+    "min_temp": 0.75,
+    "max_temp": 0.95,
+    "dynatemp_exponent": 1,
+    "smoothing_factor": 0,
+    "smoothing_curve": 1,
+    "add_bos_token": true,
+    "truncation_length": 2048,
+    "ban_eos_token": false,
+    "skip_special_tokens": false,
+    "streaming": true,
+    "mirostat_mode": 0,
+    "mirostat_tau": 6,
+    "mirostat_eta": 0.29,
+    "guidance_scale": 1,
+    "negative_prompt": "",
+    "grammar_string": "",
+    "banned_tokens": "",
+    "sampler_priority": [
+        "temperature",
+        "dynamic_temperature",
+        "quadratic_sampling",
+        "top_k",
+        "top_p",
+        "typical_p",
+        "epsilon_cutoff",
+        "eta_cutoff",
+        "tfs",
+        "top_a",
+        "min_p",
+        "mirostat"
+    ],
+    "samplers": [
+        "top_k",
+        "tfs_z",
+        "typical_p",
+        "top_p",
+        "min_p",
+        "temperature"
+    ],
+    "ignore_eos_token_aphrodite": false,
+    "spaces_between_special_tokens_aphrodite": true,
+    "sampler_order": [
+        6,
+        0,
+        1,
+        3,
+        4,
+        2,
+        5
+    ],
+    "logit_bias": [],
+    "n": 1,
+    "rep_pen_size": 0,
+    "genamt": 256,
+    "max_length": 8192
+}