Add models

Signed-off-by: Xin Liu <[email protected]>

.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

Octopus-v2-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476b2976ac703ad133e32d6aa0093b0578ccdfe6142fcb4e2ae70805b7171132
+size 1157962112

Octopus-v2-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bfe3fbf7db18148474b27229009cabc2c9c4b85f9e0d75835e572f1983e658c
+size 1465629056

Octopus-v2-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dd5255af4f2ddcb84aab91355bc3b3b6dc8ad29f36c49a803199941093b517
+size 1383840128

Octopus-v2-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cbdecf73caddbe0d69d019081d55f2efb101cbe46f082577d245391566ed2b
+size 1288018304

Octopus-v2-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3647fa1db4fbe3feaf3a09c86e63519320aaf11a4b3f8c1fe0650cb758ea80fc
+size 1551227264

Octopus-v2-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f84a9bd4c9d51e41ce4fdbf26083f9388480db59a0cc965f010ae952b613788e
+size 1630300544

Octopus-v2-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da4615a35f6ab409c086e5b47a7014b61d97231a15e34d521f768572f2c8b4ba
+size 1559878016

Octopus-v2-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:391820dba753f015fd48afd78d214861e75356047e021e52addcff52ed68b460
+size 1798953344

Octopus-v2-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b04c7e54cbc458e3fc9fe420e217a31eee684610b43bf70f024667021d36f85
+size 1839688064

Octopus-v2-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d040707233e46483d0db272db6704ba95e8b864948dc7662ddc16c02123cc03c
+size 1798953344

Octopus-v2-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5bc54dc52cbd805fd3094b11e2d2ce3be477d8a6e84c6776aa5d3583a5065a9
+size 2062162304

Octopus-v2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad33a16d4544c0a6e02ea57a3081993fac8819c23767d38ba9ec1a588ca5fe04
+size 2669118496

Octopus-v2-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ecc5f1a0e8fea834cae503dd043560886cdd66ad38a669589bcc3d7a8806374
+size 5018626272

README.md

@@ -1,3 +1,52 @@
 ---
+language:
+- en
 license: apache-2.0
+model_name: Octopus-V2-2B
+base_model: NexaAIDev/Octopus-v2
+inference: false
+model_creator: NexaAIDev
+quantized_by: Second State Inc.
+tags:
+- function calling
+- on-device language model
+- android
 ---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Octopus-v2-2B-GGUF
+
+## Original Model
+
+[NexaAIDev/Octopus-v2](https://huggingface.co/NexaAIDev/Octopus-v2)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: coming soon
+
+- Context size: `2048`
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-2-7b-chat-hf-Q2_K.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q2_K.gguf)     | Q2_K   | 2 | 2.83 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-2-7b-chat-hf-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_L.gguf) | Q3_K_L | 3 | 3.6 GB| small, substantial quality loss |
+| [Llama-2-7b-chat-hf-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_M.gguf) | Q3_K_M | 3 | 3.3 GB| very small, high quality loss |
+| [Llama-2-7b-chat-hf-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| very small, high quality loss |
+| [Llama-2-7b-chat-hf-Q4_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_0.gguf)     | Q4_0   | 4 | 3.83 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-2-7b-chat-hf-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| medium, balanced quality - recommended |
+| [Llama-2-7b-chat-hf-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| small, greater quality loss |
+| [Llama-2-7b-chat-hf-Q5_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_0.gguf)     | Q5_0   | 5 | 4.65 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-2-7b-chat-hf-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| large, very low quality loss - recommended |
+| [Llama-2-7b-chat-hf-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
+| [Llama-2-7b-chat-hf-Q6_K.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q6_K.gguf)     | Q6_K   | 6 | 5.53 GB| very large, extremely low quality loss |
+| [Llama-2-7b-chat-hf-Q8_0.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-Q8_0.gguf)     | Q8_0   | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
+| [Llama-2-7b-chat-hf-f16.gguf](https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/blob/main/Llama-2-7b-chat-hf-f16.gguf)     | f16   | 16 | 13.5 GB|  |

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "NexaAIDev/gemma-2b-base",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256022
+}