初始化项目，由ModelHub XC社区提供模型

Model: RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,57 @@
+*.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
+llama-3-experiment-v1-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-experiment-v1-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,225 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+llama-3-experiment-v1-9B - GGUF
+- Model creator: https://huggingface.co/grimjim/
+- Original model: https://huggingface.co/grimjim/llama-3-experiment-v1-9B/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [llama-3-experiment-v1-9B.Q2_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q2_K.gguf) | Q2_K | 3.26GB |
+| [llama-3-experiment-v1-9B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_XS.gguf) | IQ3_XS | 3.61GB |
+| [llama-3-experiment-v1-9B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_S.gguf) | IQ3_S | 3.78GB |
+| [llama-3-experiment-v1-9B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_S.gguf) | Q3_K_S | 3.76GB |
+| [llama-3-experiment-v1-9B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ3_M.gguf) | IQ3_M | 3.88GB |
+| [llama-3-experiment-v1-9B.Q3_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K.gguf) | Q3_K | 4.13GB |
+| [llama-3-experiment-v1-9B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_M.gguf) | Q3_K_M | 4.13GB |
+| [llama-3-experiment-v1-9B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q3_K_L.gguf) | Q3_K_L | 4.45GB |
+| [llama-3-experiment-v1-9B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ4_XS.gguf) | IQ4_XS | 4.61GB |
+| [llama-3-experiment-v1-9B.Q4_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_0.gguf) | Q4_0 | 4.8GB |
+| [llama-3-experiment-v1-9B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.IQ4_NL.gguf) | IQ4_NL | 4.84GB |
+| [llama-3-experiment-v1-9B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K_S.gguf) | Q4_K_S | 4.83GB |
+| [llama-3-experiment-v1-9B.Q4_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K.gguf) | Q4_K | 5.07GB |
+| [llama-3-experiment-v1-9B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_K_M.gguf) | Q4_K_M | 5.07GB |
+| [llama-3-experiment-v1-9B.Q4_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q4_1.gguf) | Q4_1 | 5.29GB |
+| [llama-3-experiment-v1-9B.Q5_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_0.gguf) | Q5_0 | 5.77GB |
+| [llama-3-experiment-v1-9B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K_S.gguf) | Q5_K_S | 5.77GB |
+| [llama-3-experiment-v1-9B.Q5_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K.gguf) | Q5_K | 5.91GB |
+| [llama-3-experiment-v1-9B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_K_M.gguf) | Q5_K_M | 5.91GB |
+| [llama-3-experiment-v1-9B.Q5_1.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q5_1.gguf) | Q5_1 | 6.26GB |
+| [llama-3-experiment-v1-9B.Q6_K.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q6_K.gguf) | Q6_K | 6.81GB |
+| [llama-3-experiment-v1-9B.Q8_0.gguf](https://huggingface.co/RichardErkhov/grimjim_-_llama-3-experiment-v1-9B-gguf/blob/main/llama-3-experiment-v1-9B.Q8_0.gguf) | Q8_0 | 8.82GB |
+
+
+
+
+Original model description:
+---
+language:
+- en
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+library_name: transformers
+tags:
+- meta
+- llama-3
+- pytorch
+- mergekit
+- merge
+license: llama3
+license_link: LICENSE
+pipeline_tag: text-generation
+widget:
+  - example_title: Hello
+    messages:
+    - role: user
+      content: Hey my name is Corwin! How are you?
+  - example_title: Hellriding out of Amber
+    messages:
+    - role: system
+      content: You are a helpful and honest assistant. Please, respond concisely and truthfully.
+    - role: user
+      content: Can you recommend a good destination for a hellride out of Amber?
+inference:
+  parameters:
+    max_new_tokens: 300
+    stop:
+    - <|end_of_text|>
+    - <|eot_id|>
+model-index:
+- name: grimjim/grimjim/llama-3-experiment-v1-9B
+  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: 66.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/grimjim/llama-3-experiment-v1-9B
+      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: 78.56
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
+      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: 66.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
+      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: 50.7
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
+      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: 75.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
+      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: 65.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=grimjim/llama-3-experiment-v1-9B
+      name: Open LLM Leaderboard
+---
+# llama-3-experiment-v1-9B
+
+This is an experimental merge, replicating additional layers to the model without post-merge healing.
+There is damage to the model, but it appears to be tolerable as is; the performance difference in benchmarks from the original 8B Instruct model does not appear to be significant.
+The resulting impact on narrative text completion may also be of interest.
+
+Light testing performed with instruct prompting and the following sampler settings:
+- temp=1 and minP=0.02
+- temp=1 and smoothing factor=0.33
+
+Full weights: [grimjim/llama-3-experiment-v1-9B](https://huggingface.co/grimjim/llama-3-experiment-v1-9B)
+
+GGUF quants: [grimjim/llama-3-experiment-v1-9B-GGUF](https://huggingface.co/grimjim/llama-3-experiment-v1-9B-GGUF)
+
+This is a merge of pre-trained language model meta-llama/Meta-Llama-3-8B-Instruct created using [mergekit](https://github.com/cg123/mergekit).
+
+Built with Meta Llama 3.
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* meta-llama/Meta-Llama-3-8B-Instruct
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+    - model: meta-llama/Meta-Llama-3-8B-Instruct
+      layer_range: [0, 12]
+  - sources:
+    - model: meta-llama/Meta-Llama-3-8B-Instruct
+      layer_range: [8, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```
+
+

llama-3-experiment-v1-9B.IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883aee4bf99db28531ac56f6cbbb471e503e2c06b3511fc3313569e611d31be5
+size 4170963328

llama-3-experiment-v1-9B.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cca839e5de2f478f8973e9ffd8b34565f60ed861cc5a8e9b034d70f914d3734
+size 4059552128

llama-3-experiment-v1-9B.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c590b869071d4005ef52dea70cf776d79c02aeda6a5c8aac9c4cb392c9f58f
+size 3875527040

llama-3-experiment-v1-9B.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed9acb37451bd1a38bd63411b175f09fa21afaa70055e0c06dfc592fe26eab0
+size 5200312704

llama-3-experiment-v1-9B.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36148127a373c290f21ede93e2d50794c76bb9d91e2bd9d7a23a1cec7566b832
+size 4950587776

llama-3-experiment-v1-9B.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7b15b9e7ee6a7dc85d88df0c6cac45af3363abba35aec44a508498986d08ec
+size 3500128640

llama-3-experiment-v1-9B.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175d2dd4d40ef4c2cc6850c8c8d12a45c61900805c6696ff26fe92f422fa2387
+size 4436253056

llama-3-experiment-v1-9B.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699300db7a722ba670ee647759d63628e4a44d844ace2f05d01f01eb82f4405b
+size 4779137408

llama-3-experiment-v1-9B.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175d2dd4d40ef4c2cc6850c8c8d12a45c61900805c6696ff26fe92f422fa2387
+size 4436253056

llama-3-experiment-v1-9B.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2399711c0a3ebb73045d1f888f160826280d74e447c5e1ea4eecda441d9666
+size 4039498112

llama-3-experiment-v1-9B.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957f4cfd6e5381bd6fce59f691894383237c6485eaf7101a4bc83c966be541fc
+size 5152078208

llama-3-experiment-v1-9B.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700d41f2fa77da004eb9ed128f6fe8ecd64fac51424a7b28ba8c770dca78b48e
+size 5675645312

llama-3-experiment-v1-9B.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c077ae081dc527e2b362a015f3f84614c7565bbdbfeb0f77a329cc38e98aa527
+size 5444041088

llama-3-experiment-v1-9B.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c077ae081dc527e2b362a015f3f84614c7565bbdbfeb0f77a329cc38e98aa527
+size 5444041088

llama-3-experiment-v1-9B.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ee58d2835ecdd5b674be3fcd214b9a98ba5a678bb4fe01acbea27810f907a7
+size 5183535488

llama-3-experiment-v1-9B.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e543a1f4895e8d56cd13ee006e845161322be8161c89013130ba34402f0b7e
+size 6199212416

llama-3-experiment-v1-9B.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b120ce02044cf9c14bba4dc9ba854538ba2f872a21d26fc4790b3a392f312f97
+size 6722779520

llama-3-experiment-v1-9B.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04b957cb7b40aecfcaa19b4cfd7a12526eadf44f6f89124462653724db4eb87
+size 6349617536

llama-3-experiment-v1-9B.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e04b957cb7b40aecfcaa19b4cfd7a12526eadf44f6f89124462653724db4eb87
+size 6349617536

llama-3-experiment-v1-9B.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a84150ee64d70b85d63d228941de35002d96bbb4d8e57de51b54ab7862277e
+size 6199212416

llama-3-experiment-v1-9B.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efb232fa4c3471db33a12544dcf41e7d35455db99c946865c24687d914bcaf1
+size 7311792512

llama-3-experiment-v1-9B.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123f3be2b901b93d84759db33ac710d417141f3fd326bb68fbf1c7dfd205d5d2
+size 9467844992