初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama-68M-Chat-v1-i1-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-68M-Chat-v1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-68M-Chat-v1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Llama-68M-Chat-v1.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2245678a816d6cf1c5fc81742cb64b1896869a73446d63813695eb03854c2145
+size 30007968

Llama-68M-Chat-v1.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce4258488dab4289c223d92af3b6277373fa74055e3e5a534e22233185ca0f6
+size 29620896

Llama-68M-Chat-v1.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce3c8a9dc5fd271a2fe6cb305c2ab79b14582b8e1843eb62517ff73e616b2ad
+size 34503840

Llama-68M-Chat-v1.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161e7d638504b4a9cfaff52d639a4691793797a8a958b17664b6da7d6824c9e9
+size 33987744

Llama-68M-Chat-v1.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad9050cce0d29069b89b44ae68b8b0e3b0901af69265e19bc77eb4951c58e47
+size 31206048

Llama-68M-Chat-v1.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de817205037f6eff0e6d15ee1a496824da72b87a1e744de5d7e2387230fc30d
+size 30653088

Llama-68M-Chat-v1.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6435586bf392c87490872f6570f07874ad7b60449bde0452e4dc750a308eb70f
+size 39887520

Llama-68M-Chat-v1.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b7b2234e7d9ceb741438a4cba755b69784a930724247c804f5c68ccd747e79
+size 39574176

Llama-68M-Chat-v1.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5788c70b3cd2c6100678a560163fe300926cb109993aafd0e382837e3a3279
+size 39242400

Llama-68M-Chat-v1.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a51c78fd039b3644df49f9f90580c0b9bbd2cd88f2889378b25c621c00910812
+size 35333280

Llama-68M-Chat-v1.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d155947351271c92c979ce0511d11f8dd4de9d2ebbb6418023559c353b11f3
+size 43987104

Llama-68M-Chat-v1.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa8e0b9166917983e244eddbce1afa09d244d95a8a55e5da9bce5a079b49de9
+size 35880096

Llama-68M-Chat-v1.i1-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcca1b77b3bde3716a886e0a82c7f512fb3d7a9a323ee1aabc4e3ae6221fafe6
+size 35161248

Llama-68M-Chat-v1.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b64d1c7d96881a13e61acc26baff975e2df46fb83116d19045e5f13b4881ea
+size 41398944

Llama-68M-Chat-v1.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593dd954792c258814b26eaf211b0d6190a51c6e53e105349c4e7f3dde8bfb9d
+size 40661664

Llama-68M-Chat-v1.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c5a52c0f284fac11b288c451a2fc17e108bdbbb2dd226b4a51dd283b178503
+size 39574176

Llama-68M-Chat-v1.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3a0af606f20c28a14bb7501fa1a5f69a079bdb60a97ee35c02be799d63a18f
+size 45344928

Llama-68M-Chat-v1.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a8b9691db1de2f25c4667f7acb8e2e7dc55169e9f7222d270c9bc60fe93c97
+size 46105248

Llama-68M-Chat-v1.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126b3ebce90d6d47edb723eed6b80f4e85bfd92e48d1da29753032dfa51de152
+size 45492384

Llama-68M-Chat-v1.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b518d7dfdbda06390a04a00c3ad13f94fa755ba2365d7cc518760946108840
+size 51167904

Llama-68M-Chat-v1.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fa0e103cab111d985e739cc1f00c8df8fceb345d732fdb0fdcbdf18dca681d
+size 50776224

Llama-68M-Chat-v1.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac93a11ee21433846e41e80c5268577bc9cc0115f5c51671291c1a4afe6e8fc
+size 56546976

README.md

@@ -0,0 +1,86 @@
+---
+base_model: Felladrin/Llama-68M-Chat-v1
+datasets:
+- THUDM/webglm-qa
+- databricks/databricks-dolly-15k
+- cognitivecomputations/wizard_vicuna_70k_unfiltered
+- totally-not-an-llm/EverythingLM-data-V3
+- Amod/mental_health_counseling_conversations
+- sablo/oasst2_curated
+- starfishmedical/webGPT_x_dolly
+- Open-Orca/OpenOrca
+- mlabonne/chatml_dpo_pairs
+language:
+- en
+library_name: transformers
+license: apache-2.0
+quantized_by: mradermacher
+tags:
+- text-generation
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/Felladrin/Llama-68M-Chat-v1
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Llama-68M-Chat-v1-GGUF
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.1 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.1 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.1 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.1 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q2_K.gguf) | i1-Q2_K | 0.1 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.1 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.1 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.1 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.1 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q4_0.gguf) | i1-Q4_0 | 0.1 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.1 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-68M-Chat-v1-i1-GGUF/resolve/main/Llama-68M-Chat-v1.i1-Q6_K.gguf) | i1-Q6_K | 0.2 | practically like static Q6_K |
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## FAQ / Model Request
+
+See https://huggingface.co/mradermacher/model_requests for some answers to
+questions you might have and/or if you want some other model quantized.
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->