初始化项目，由ModelHub XC社区提供模型

Model: icefog72/IceLemonTeaRP-32k-7b Source: Original Platform
2026-04-12 16:11:00 +08:00
commit d2f3043075
12 changed files with 154056 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 +1,342 @@
+---
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- mergekit
+- merge
+- alpaca
+- mistral
+- not-for-all-audiences
+- nsfw
+base_model:
+- icefog72/Kunokukulemonchini-32k-7b
+- icefog72/Mixtral_AI_Cyber_3.m1-BigL
+- grimjim/kukulemon-32K-7B
+- LeroyDyer/Mixtral_AI_Cyber_3.m1
+- Nitral-AI/Kunocchini-7b-128k-test
+- Undi95/BigL-7B
+model-index:
+- name: IceLemonTeaRP-32k-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: 67.66
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 86.53
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 64.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 61.76
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 79.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-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: 62.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 52.12
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 30.14
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.83
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 5.37
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 12.2
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 22.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceLemonTeaRP-32k-7b
+      name: Open LLM Leaderboard
+---
+# IceLemonTeaRP-32k-7b
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63407b719dbfe0d48b2d763b/PSpmU4l79CrdfzbCd-xSf.png)
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+I would suggest to play with rope_theta in config.json to set between 40000-100000.
+
+## Merge Details
+
+Cooked merge from fresh ingredients to fix [icefog72/IceTeaRP-7b](https://huggingface.co/icefog72/IceTeaRP-7b) repetition problems.
+
+Prompt template: Alpaca, maybe ChatML
+
+* measurement.json for quanting exl2 included. 
+
+- [IceLemonTeaRP-32k-7b-4.0bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-4.0bpw-h6-exl2)
+- [IceLemonTeaRP-32k-7b-4.2bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-4.2bpw-h6-exl2)
+- [IceLemonTeaRP-32k-7b-6.5bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-6.5bpw-h6-exl2)
+- [IceLemonTeaRP-32k-7b-8.0bpw-h6-exl2](https://huggingface.co/icefog72/IceLemonTeaRP-32k-7b-8.0bpw-h6-exl2)
+
+Thanks for 
+- [mradermacher/IceTeaRP-7b-GGUF](https://huggingface.co/mradermacher/IceLemonTeaRP-32k-7b-GGUF)
+- [Natkituwu/IceLemonTeaRP-32k-7b-7.1bpw-exl2](https://huggingface.co/Natkituwu/IceLemonTeaRP-32k-7b-7.1bpw-exl2)
+
+### Merge Method
+
+This model was merged using the SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* icefog72/Kunokukulemonchini-32k-7b
+  * [grimjim/kukulemon-32K-7B](https://huggingface.co/grimjim/kukulemon-32K-7B)
+  * [Nitral-AI/Kunocchini-7b-128k-test](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test)
+* icefog72/Mixtral_AI_Cyber_3.m1-BigL
+  * [LeroyDyer/Mixtral_AI_Cyber_3.m1](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_3.m1)
+  * [Undi95/BigL-7B](https://huggingface.co/Undi95/BigL-7B)
+
+## How to download From the command line
+
+I recommend using the `huggingface-hub` Python library:
+
+```shell
+pip3 install huggingface-hub
+```
+
+To download the `main` branch to a folder called `IceLemonTeaRP-32k-7b`:
+
+```shell
+mkdir IceLemonTeaRP-32k-7b
+huggingface-cli download icefog72/IceLemonTeaRP-32k-7b --local-dir IceLemonTeaRP-32k-7b --local-dir-use-symlinks False
+```
+
+<details>
+  <summary>More advanced huggingface-cli download usage</summary>
+
+If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
+
+The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
+
+For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
+
+To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
+
+```shell
+pip3 install hf_transfer
+```
+
+And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
+
+```shell
+mkdir FOLDERNAME
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MODEL --local-dir FOLDERNAME --local-dir-use-symlinks False
+```
+
+Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
+</details>
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+slices:
+  - sources:
+      - model: Mixtral_AI_Cyber_3.m1-BigL
+        layer_range: [0, 32]
+      - model: Kunokukulemonchini-32k-7b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Kunokukulemonchini-32k-7b
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: float16
+```
+
+# [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_icefog72__IceLemonTeaRP-32k-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |70.43|
+|AI2 Reasoning Challenge (25-Shot)|67.66|
+|HellaSwag (10-Shot)              |86.53|
+|MMLU (5-Shot)                    |64.51|
+|TruthfulQA (0-shot)              |61.76|
+|Winogrande (5-shot)              |79.72|
+|GSM8k (5-shot)                   |62.40|
+
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_icefog72__IceLemonTeaRP-32k-7b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.27|
+|IFEval (0-Shot)    |52.12|
+|BBH (3-Shot)       |30.14|
+|MATH Lvl 5 (4-Shot)| 4.83|
+|GPQA (0-shot)      | 5.37|
+|MuSR (0-shot)      |12.20|
+|MMLU-PRO (5-shot)  |22.97|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "D:\\FModels\\Kunokukulemonchini-32k-7b",
+  "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": 100000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/measurement.json
+++ b/measurement.json
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: D:\FModels\Mixtral_AI_Cyber_3.m1-BigL
+        layer_range: [0, 32]
+      - model: D:\FModels\Kunokukulemonchini-32k-7b
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: D:\FModels\Kunokukulemonchini-32k-7b
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: float16
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fea0f9e5651fd9c8b98aa5788e7d8a9462ca65e5b7f478748d03aa43e581f7
+size 9970219384
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a96e8693b99af873f05cdf0bf0cf622dd92db4a56da1824edfd8cf1cf4c700
+size 4513278344
--- 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
+}