初始化项目，由ModelHub XC社区提供模型

Model: saishf/Fett-Eris-Mix-7B Source: Original Platform
2026-05-21 09:10:16 +08:00
commit 9bdf6a4004
17 changed files with 91474 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,178 @@
+---
+language:
+- en
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- Epiculous/Fett-uccine-7B
+- eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
+- OpenPipe/mistral-ft-optimized-1227
+- ChaoticNeutrals/Eris_7B
+pipeline_tag: text-generation
+model-index:
+- name: Fett-Eris-Mix-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 68.77
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 87.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 63.65
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 71.91
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 80.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 57.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Fett-Eris-Mix-7B
+      name: Open LLM Leaderboard
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+* This model is an attempt at making a smart rp model with the finesse of [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B).
+* From limited testing i've found it to be my favourite of my personal 7B models. It stays pretty coherent at 8k+ ctx.
+* I like to use "Alpaca" format with "Universal-Light" for longer messages. Switching to ChatML causes the messages to be much shorter? I haven't a clue why but sometimes it's nice.
+* It doesn't seem to show many issues but i'd be willing to try to fix any problems or bugs as it shows some potential. 
+### Merge Method
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Epiculous/Fett-uccine-7B](https://huggingface.co/Epiculous/Fett-uccine-7B)
+* [eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2](https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2)
+* [ChaoticNeutrals/Eris_7B](https://huggingface.co/ChaoticNeutrals/Eris_7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: OpenPipe/mistral-ft-optimized-1227
+    # No parameters necessary for base model
+  - model: Epiculous/Fett-uccine-7B
+    parameters:
+      density: 0.53
+      weight: 0.4
+  - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
+    parameters:
+      density: 0.53
+      weight: 0.35
+  - model: ChaoticNeutrals/Eris_7B
+    parameters:
+      density: 0.53
+      weight: 0.25
+merge_method: dare_ties
+base_model: OpenPipe/mistral-ft-optimized-1227
+parameters:
+  int8_mask: true
+dtype: bfloat16
+
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_saishf__Fett-Eris-Mix-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |71.66|
+|AI2 Reasoning Challenge (25-Shot)|68.77|
+|HellaSwag (10-Shot)              |87.33|
+|MMLU (5-Shot)                    |63.65|
+|TruthfulQA (0-shot)              |71.91|
+|Winogrande (5-shot)              |80.82|
+|GSM8k (5-shot)                   |57.47|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "OpenPipe/mistral-ft-optimized-1227",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,20 @@
+models:
+  - model: OpenPipe/mistral-ft-optimized-1227
+    # No parameters necessary for base model
+  - model: Epiculous/Fett-uccine-7B
+    parameters:
+      density: 0.53
+      weight: 0.4
+  - model: eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-v2
+    parameters:
+      density: 0.53
+      weight: 0.35
+  - model: ChaoticNeutrals/Eris_7B
+    parameters:
+      density: 0.53
+      weight: 0.25
+merge_method: dare_ties
+base_model: OpenPipe/mistral-ft-optimized-1227
+parameters:
+  int8_mask: true
+dtype: bfloat16
--- a/model-00001-of-00008.safetensors
+++ b/model-00001-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6593e42b8fe8e77db6e089cdbfc1f436873dab47026e09dc7cf0ef0be44df8d8
+size 1979773128
--- a/model-00002-of-00008.safetensors
+++ b/model-00002-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e29a4a86bcd7097a5fbe2e0dd3822ad604e9b0084d540aa007e4fc705b6a9c7
+size 1946235640
--- a/model-00003-of-00008.safetensors
+++ b/model-00003-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd75752c9816f7354cb2aacba516ac17de3f337c0c64f0e130a6cc278ad2b7ab
+size 1973490216
--- a/model-00004-of-00008.safetensors
+++ b/model-00004-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9045f1a82325fda06d2aa55198fffb2bead74313d1b04c6bd1bb374cc41a7349
+size 1979781464
--- a/model-00005-of-00008.safetensors
+++ b/model-00005-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71b41d3fcebf95d054643606e6c58c017718dba41aac75d684a5d043b7b3f26
+size 1946243984
--- a/model-00006-of-00008.safetensors
+++ b/model-00006-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f51c9c14d0e56e30ab96b02890b24e14cc2a31d65859158e3276b20d9295c3
+size 1923166040
--- a/model-00007-of-00008.safetensors
+++ b/model-00007-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa1338ad4ea3a613d8be725224a4ab798afa71c7cc80e7696c6b9f2d61f2057
+size 1946243984
--- a/model-00008-of-00008.safetensors
+++ b/model-00008-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757101f6b0ff07e46f82cc9070e27fd8385082fdfb0c507f762e678eeb20157d
+size 788563544
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}