初始化项目，由ModelHub XC社区提供模型

Model: ChaoticNeutrals/Pasta-Lake-7b Source: Original Platform
2026-05-11 22:50:59 +08:00
commit 2b2206497b
19 changed files with 91525 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 +1,167 @@
+---
+license: other
+library_name: transformers
+tags:
+- mergekit
+- merge
+base_model:
+- Test157t/Pasta-PrimaMaid-7b
+- macadeliccc/WestLake-7B-v2-laser-truthy-dpo
+model-index:
+- name: Pasta-Lake-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: 70.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 87.91
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 64.41
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 68.28
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 82.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-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: 64.37
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Test157t/Pasta-Lake-7b
+      name: Open LLM Leaderboard
+---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/Q-4HMjTgR6cpLnuW6Ghk3.png)
+Thanks to @Kooten the man the myth the legend we have exl2 quants: https://huggingface.co/models?search=Kooten/Pasta-Lake-7b-exl2
+
+Thanks to @bartowski the homie for the additional exl2 quants, please show him some support aswell: https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/main 
+
+Thanks also to @konz00 for the gguf quants: https://huggingface.co/konz00/Pasta-Lake-7b-GGUF
+
+Thanks to @Lewdiculus for the other GGUF quants: https://huggingface.co/Lewdiculous/Pasta-Lake-7b-GGUF
+
+added ST preset files
+
+### Models Merged
+
+The following models were included in the merge:
+* [Test157t/Pasta-PrimaMaid-7b](https://huggingface.co/Test157t/Pasta-PrimaMaid-7b)
+* [macadeliccc/WestLake-7B-v2-laser-truthy-dpo](https://huggingface.co/macadeliccc/WestLake-7B-v2-laser-truthy-dpo)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: Test157t/Pasta-PrimaMaid-7b
+        layer_range: [0, 32]
+      - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Test157t/Pasta-PrimaMaid-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
+```
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/dfYLzaMs5KU4BtbQQKzat.png)
+# [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_Test157t__Pasta-Lake-7b)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |73.07|
+|AI2 Reasoning Challenge (25-Shot)|70.82|
+|HellaSwag (10-Shot)              |87.91|
+|MMLU (5-Shot)                    |64.41|
+|TruthfulQA (0-shot)              |68.28|
+|Winogrande (5-shot)              |82.64|
+|GSM8k (5-shot)                   |64.37|
+
--- a/PRESETS/Default-Context_With_Trimming.json
+++ b/PRESETS/Default-Context_With_Trimming.json
@@ -0,0 +1,11 @@
+{
+    "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": false,
+    "always_force_name2": false,
+    "trim_sentences": true,
+    "include_newline": false,
+    "single_line": false,
+    "name": "Default- With Trimming"
+}
--- a/PRESETS/Yes_This_Is_a_Textgen_Preset.json
+++ b/PRESETS/Yes_This_Is_a_Textgen_Preset.json
@@ -0,0 +1,57 @@
+{
+    "temp": 1,
+    "temperature_last": true,
+    "top_p": 1,
+    "top_k": 0,
+    "top_a": 0,
+    "tfs": 1,
+    "epsilon_cutoff": 0,
+    "eta_cutoff": 0,
+    "typical_p": 1,
+    "min_p": 0.05,
+    "rep_pen": 1,
+    "rep_pen_range": 0,
+    "no_repeat_ngram_size": 0,
+    "penalty_alpha": 0,
+    "num_beams": 1,
+    "length_penalty": 0,
+    "min_length": 0,
+    "encoder_rep_pen": 1,
+    "freq_pen": 0,
+    "presence_pen": 0,
+    "do_sample": true,
+    "early_stopping": false,
+    "dynatemp": false,
+    "min_temp": 1,
+    "max_temp": 5,
+    "dynatemp_exponent": 1,
+    "smoothing_factor": 0.25,
+    "add_bos_token": true,
+    "truncation_length": 2048,
+    "ban_eos_token": false,
+    "skip_special_tokens": false,
+    "streaming": false,
+    "mirostat_mode": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "guidance_scale": 1,
+    "negative_prompt": "",
+    "grammar_string": "",
+    "banned_tokens": "",
+    "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": 200,
+    "max_length": 8192
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Test157t/Pasta-PrimaMaid-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": 8192,
+  "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": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: Test157t/Pasta-PrimaMaid-7b
+        layer_range: [0, 32]
+      - model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Test157t/Pasta-PrimaMaid-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-00008.safetensors
+++ b/model-00001-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3365ecbe803105bcdc4a0bafd8f3062bb889d4c2d35e61d94d4ff22b5e84af48
+size 1946227288
--- 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:dbe74bb32464e6e555f3bbc7ef345c5781065f5ad7fbabe015fc4422742302ff
+size 1946227304
--- 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 sha256:429f1f3592781dc46f62105f0b8257b9382e091300fa13737319d4d6d1c75e95
+size 1889603632
--- 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 sha256:108f148590ead4c1fa2a5ee3392276f49ac64ad6ea84ba4a42c309232b867a3e
+size 1979789712
--- 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:e21834c35da83b59a08b11a187cd7445e5d6d5d71f92190d84c00deb1c1d6f8b
+size 1979781424
--- 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:cf2fa49d04d8982c4c375a680eb87174abde0f65c5dd5701c363ba3fbf15ab7b
+size 1979806336
--- 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:fe2cb036458d63811e6df53e1ad3af96e98d67f50b6519b0ac93c4cadac752d1
+size 1889595336
--- 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 sha256:4229e02e2852c89511982db11b70301c546b9a46227d9f2f537be251f3a56c96
+size 872466680
--- 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 +1,40 @@
+{
+  "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
+}