Llamacpp quants

.gitattributes

@@ -33,3 +33,16 @@ saved_model/**/* 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
+ChatHercules-2.5-Mistral-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+ChatHercules-2.5-Mistral-7B-fp16.gguf filter=lfs diff=lfs merge=lfs -text

ChatHercules-2.5-Mistral-7B-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a8fd80721d24f5c6eeb28c89761af46622a604617e7bfc3ec13140c44201013
+size 2719241984

ChatHercules-2.5-Mistral-7B-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f60938d79bfab5cc197e8e9734cfd118c9e889bc0c2790d7fb591df5352f375
+size 3822024448

ChatHercules-2.5-Mistral-7B-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8172d393483a074f9f09ff09fc0aacd7fa2ff8f0ea68946a6d8a24b3ba71807f
+size 3518985984

ChatHercules-2.5-Mistral-7B-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2b412a816fd0a061f7b5aa5ba12bc83aff727debb7693e6162605e9bf1be9e
+size 3164567296

ChatHercules-2.5-Mistral-7B-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e892a7c4fb7de767a08683c3d91197b716731e15ff4a800ec324074a68c00bd
+size 4108916480

ChatHercules-2.5-Mistral-7B-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4854548523dcea22461b61fbca2c35408621f960b32d1b7cff945d557b0138a2
+size 4368439040

ChatHercules-2.5-Mistral-7B-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca0a10b031c7e9935ad0c97d8230bc31e8c7942b90401cc93b4ed92a50c6faf
+size 4140373760

ChatHercules-2.5-Mistral-7B-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446d2eb3535793d69a9dd890a8a445cb06c67c8523cf99fefa7df6222693ae04
+size 4997715712

ChatHercules-2.5-Mistral-7B-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c08f879ab41c336a6b84c23e4e2bf4093932e3ff7ee577e91c4c5e5d0426099
+size 5131409152

ChatHercules-2.5-Mistral-7B-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e854f137947974dcbf1612d7e81e12f6d62fbe51b26b44a44131d598e2eb464
+size 4997715712

ChatHercules-2.5-Mistral-7B-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd9a5e297c8c97d65259e0ae9cf46c0a94330d6f6ceeec21f411fb0eaddd107
+size 5942064896

ChatHercules-2.5-Mistral-7B-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8178bca03a99fe478a655889ae7b26d6566a3766842582157432452489532bc
+size 7695857408

ChatHercules-2.5-Mistral-7B-fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1b181e67ec950aa81d5dc1fa0306088373b1e8ea4f87d0d60875bfd5586444
+size 14484731584

README.md

@@ -0,0 +1,142 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Locutusque/Hercules-2.5-Mistral-7B
+- openchat/openchat-3.5-0106
+base_model:
+- Locutusque/Hercules-2.5-Mistral-7B
+- openchat/openchat-3.5-0106
+model-index:
+- name: ChatHercules-2.5-Mistral-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: 65.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-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: 84.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-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: 65.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-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: 47.52
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-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: 81.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-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: 64.97
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=hydra-project/ChatHercules-2.5-Mistral-7B
+      name: Open LLM Leaderboard
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Llamacpp Quantizations of ChatHercules-2.5-Mistral-7B
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2334">b2334</a> for quantization.
+
+Original model: https://huggingface.co/hydra-project/ChatHercules-2.5-Mistral-7B
+
+Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [ChatHercules-2.5-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
+| [ChatHercules-2.5-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
+| [ChatHercules-2.5-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
+| [ChatHercules-2.5-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
+| [ChatHercules-2.5-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
+| [ChatHercules-2.5-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
+| [ChatHercules-2.5-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
+| [ChatHercules-2.5-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
+| [ChatHercules-2.5-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
+| [ChatHercules-2.5-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
+| [ChatHercules-2.5-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
+| [ChatHercules-2.5-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/ChatHercules-2.5-Mistral-7B-GGUF/blob/main/ChatHercules-2.5-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski