Upload 9 files

.gitattributes

@@ -33,3 +33,11 @@ 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
+llama3.2-typhoon2-1b-instruct-fp16.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+llama3.2-typhoon2-1b-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,42 @@
+---
+license: llama3.2
+pipeline_tag: text-generation
+base_model: scb10x/llama3.2-typhoon2-1b-instruct
+tags:
+- llama-cpp
+- gguf-my-repo
+---
+# Float16-cloud/llama3.2-typhoon2-1b-instruct-gguf
+This model was converted to GGUF format from [`scb10x/llama3.2-typhoon2-1b-instruct`](https://huggingface.co/scb10x/llama3.2-typhoon2-1b-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/scb10x/llama3.2-typhoon2-1b-instruct) for more details on the model.
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+```bash
+brew install llama.cpp
+```
+Invoke the llama.cpp server or the CLI.
+### CLI:
+```bash
+llama-cli --hf-repo Float16-cloud/llama3.2-typhoon2-1b-instruct-gguf --hf-file llama3.2-typhoon2-1b-instruct-iq4_nl.gguf -p "The meaning to life and the universe is"
+```
+### Server:
+```bash
+llama-server --hf-repo Float16-cloud/llama3.2-typhoon2-1b-instruct-gguf --hf-file llama3.2-typhoon2-1b-instruct-iq4_nl.gguf -c 2048
+```
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo Float16-cloud/llama3.2-typhoon2-1b-instruct-gguf --hf-file llama3.2-typhoon2-1b-instruct-iq4_nl.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo Float16-cloud/llama3.2-typhoon2-1b-instruct-gguf --hf-file llama3.2-typhoon2-1b-instruct-iq4_nl.gguf -c 2048
+```

llama3.2-typhoon2-1b-instruct-fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0869a626da4ebdc3e131f6005ac4ea32b5063279c5cc7bbc8ed4083921f0e9b3
+size 2479593632

llama3.2-typhoon2-1b-instruct-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9e8cf35be920573e639c8ce57fe80d30f90c7f05e4e54e796fd6b8bda4ee7a
+size 777218208

llama3.2-typhoon2-1b-instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2cc3c3736a8903a5037460fbb1b4329f2b0de92043cfd80be53d5691cbfc53
+size 770926752

llama3.2-typhoon2-1b-instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b436d594fd08ea71cc16ddf08036f0e4184355062c69bdca6803e858bbfb0722
+size 807692448

llama3.2-typhoon2-1b-instruct-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87513cad887ce050cbc7f5a74895dc2c4f52d9c7aa7233fe04b5bc1bd329fcf
+size 892561568

llama3.2-typhoon2-1b-instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45d8f1609497a7da38dc764c23aae214991825df22152d6c3c491fdd7fd2082
+size 911501472

llama3.2-typhoon2-1b-instruct-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3c28543227357608c289e2b3b0eed01bd465c7cd1d433f3f882943c4cb2afa
+size 1021798560

llama3.2-typhoon2-1b-instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cc85781e31067b9cff450e8779a249ab0638605833ad6150197fd5c92087ce5
+size 1321080992