initial commit, with f16 to support calm

.gitattributes

@@ -33,3 +33,4 @@ 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
+*.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+base_model: PY007/TinyLlama-1.1B-Chat-v0.3
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- OpenAssistant/oasst_top1_2023-08-25
+inference: false
+language:
+- en
+license: apache-2.0
+model_creator: Zhang Peiyuan
+model_name: TinyLlama 1.1B Chat v0.3
+model_type: tinyllama
+prompt_template: '<|im_start|>system
+
+  {system_message}<|im_end|>
+
+  <|im_start|>user
+
+  {prompt}<|im_end|>
+
+  <|im_start|>assistant
+
+  '
+quantized_by: TheBloke
+---
+
+# TinyLlama 1.1B Chat v0.3 - GGUF
+
+- Model creator: [Zhang Peiyuan](https://huggingface.co/PY007)
+- Original model: [TinyLlama 1.1B Chat v0.3](https://huggingface.co/PY007/TinyLlama-1.1B-Chat-v0.3)
+- TheBloke quant: [TinyLlama-1.1B-Chat-v0.3-GGUF](https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF) 
+
+## Support for `calm`
+
+These models support the [calm]() language model runner.
+The particular quants selected for this repo are in support of [calm](https://github.com/iandennismiller/calm), which is a language model runner that automatically uses the right prompts, templates, context size, etc.
+

tinyllama-1.1b-chat-v0.3.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c49223a00c93d86eb80b9646e3f818da28bc69cfac4a943c2190dcc1b358961
+size 642763648

tinyllama-1.1b-chat-v0.3.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de14feaabf80af4d36a0fbe5927a99a24f136c2f7419b94e629df253a745d91
+size 903422400

tinyllama-1.1b-chat-v0.3.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e124f85a37ebd0ee18e78c9acc04c08463e6a1e237df103c7e1ee1a90b6528
+size 2201041440