初始化项目，由ModelHub XC社区提供模型

Model: duyntnet/Octopus-v2-imatrix-GGUF Source: Original Platform
2026-04-21 17:55:38 +08:00
commit 4f81b2c935
27 changed files with 186 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,60 @@
+*.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
+Octopus-v2-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Octopus-v2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Octopus-v2-IQ1_M.gguf
+++ b/Octopus-v2-IQ1_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0787afdf956074323b1ae140507766061d552516df61a11000a52272a1f5b4ce
+size 813875904
--- a/Octopus-v2-IQ1_S.gguf
+++ b/Octopus-v2-IQ1_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9be4e4b7e038f26b891dbb4dbc89fd69f0dd0a7a82e6516716521c70492fd8a
+size 770990784
--- a/Octopus-v2-IQ2_M.gguf
+++ b/Octopus-v2-IQ2_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba80a3b5d53247ed3c24c3198fd3c24b15ef6f7b3b4ea2b9c010e8a49beb188
+size 1019503296
--- a/Octopus-v2-IQ2_S.gguf
+++ b/Octopus-v2-IQ2_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9a9569bc07de00478cb86b4469f656fec8dfb9db7666ac16c8c10e54d9fd43
+size 962323136
--- a/Octopus-v2-IQ2_XS.gguf
+++ b/Octopus-v2-IQ2_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d1dc2a307284e0ecf11d66e60b9a99e9782f60be55dc2597f37c04af02b5b0
+size 944890560
--- a/Octopus-v2-IQ2_XXS.gguf
+++ b/Octopus-v2-IQ2_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f17030b801d7afa5f8fb73318f0e9e18194e4650377713c0d8d3c1e18d3122
+size 885351104
--- a/Octopus-v2-IQ3_M.gguf
+++ b/Octopus-v2-IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0037f33dcac14ec7df1ca764f36a21ba4a3bbcb6d7d545152812d8e696418c7a
+size 1308211744
--- a/Octopus-v2-IQ3_S.gguf
+++ b/Octopus-v2-IQ3_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb33fbea0ea0889d5d98da37fce2cc24f71c37902e52b1b3756f615ca6ce221f
+size 1289271840
--- a/Octopus-v2-IQ3_XS.gguf
+++ b/Octopus-v2-IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4db9f2702a48f159f1c8b13c625aa396b3cd57ee85c0562a34147bdd0007591
+size 1244396064
--- a/Octopus-v2-IQ3_XXS.gguf
+++ b/Octopus-v2-IQ3_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32018fb23754c4c7061d7a3397165d4d514cbb07c908319b7e3402679d648273
+size 1125409472
--- a/Octopus-v2-IQ4_NL.gguf
+++ b/Octopus-v2-IQ4_NL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ade63584f7c89759b95e177fca1c7bf626372744120d060ce78b15c52c7e3c9
+size 1552407072
--- a/Octopus-v2-IQ4_XS.gguf
+++ b/Octopus-v2-IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f30d1cb9f948b857dfbcae2f74025955e08f42d8fe0ce77455e671c0bd88e5f
+size 1490770464
--- a/Octopus-v2-Q2_K.gguf
+++ b/Octopus-v2-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ae8d964016ebb2b9fbc7b5f2282ef56c330cc6fe32868b96f58ee5a953e6bc
+size 1157962272
--- a/Octopus-v2-Q2_K_S.gguf
+++ b/Octopus-v2-Q2_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3b3704bd118ab5594e5ff9b73cfc74d512dd019a3353146f2dbb465365d8a1
+size 1104681504
--- a/Octopus-v2-Q3_K_L.gguf
+++ b/Octopus-v2-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a912ea284a7aa832f31b27b57ac25dceb41c36397a17f5711008147a1ca92f
+size 1465629216
--- a/Octopus-v2-Q3_K_M.gguf
+++ b/Octopus-v2-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba5b3305e7823340df87e6142d4c9b8a78bdcb3db1d488d6ce8e3eafec64679
+size 1383840288
--- a/Octopus-v2-Q3_K_S.gguf
+++ b/Octopus-v2-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608eb75a25c2c7a19f99140abf6242e481a46f9e46efea056ec32421b0c06e67
+size 1288018464
--- a/Octopus-v2-Q4_0.gguf
+++ b/Octopus-v2-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5777de5f00b917225480b47b42b8029c3653b585094e6b9331a3604bdb594ef
+size 1555421728
--- a/Octopus-v2-Q4_K_M.gguf
+++ b/Octopus-v2-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05b07e26e90c65f6017190462e7565264f2798b4c02c28dafd59b34a567653d
+size 1630300704
--- a/Octopus-v2-Q4_K_S.gguf
+++ b/Octopus-v2-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37adb68ead471f7fcb3018f9ee9e58b3e21236e42fc28d817459a925cc42233
+size 1559878176
--- a/Octopus-v2-Q5_0.gguf
+++ b/Octopus-v2-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deef29d8236ea0f8d66739e2f711bc85fa27268947b1680fc1df526db54948cd
+size 1803147808
--- a/Octopus-v2-Q5_K_M.gguf
+++ b/Octopus-v2-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78141788a904b22e08f535195e887ab6dee19f396df2cf057429b7626e742160
+size 1839688224
--- a/Octopus-v2-Q5_K_S.gguf
+++ b/Octopus-v2-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce9e388322c4a3e439fd81682c00d8bb05960a06879bb8b167b82550479681c8
+size 1798953504
--- a/Octopus-v2-Q6_K.gguf
+++ b/Octopus-v2-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:646720dcc3f76995e096b1ebb9c33e15b4fd2067d822e4048dba87ef6c91e630
+size 2062162464
--- a/Octopus-v2-Q8_0.gguf
+++ b/Octopus-v2-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0083af608fc5710030aa21d84d72652cc354aa12c0b94f5fd6221bed1f2a1e
+size 2669118656
--- a/README.md
+++ b/README.md
@@ -0,0 +1,51 @@
+---
+license: other
+inference: false
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- transformers
+- gguf
+- imatrix
+- NexaAIDev
+- Octopus-v2
+---
+Quantizations of https://huggingface.co/NexaAIDev/Octopus-v2
+
+# From original readme
+
+## Example Use Cases
+
+
+You can run the model on a GPU using the following code. 
+```python
+from transformers import AutoTokenizer, GemmaForCausalLM
+import torch
+import time
+
+def inference(input_text):
+    start_time = time.time()
+    input_ids = tokenizer(input_text, return_tensors="pt").to(model.device)
+    input_length = input_ids["input_ids"].shape[1]
+    outputs = model.generate(
+        input_ids=input_ids["input_ids"], 
+        max_length=1024,
+        do_sample=False)
+    generated_sequence = outputs[:, input_length:].tolist()
+    res = tokenizer.decode(generated_sequence[0])
+    end_time = time.time()
+    return {"output": res, "latency": end_time - start_time}
+
+model_id = "NexaAIDev/Octopus-v2"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = GemmaForCausalLM.from_pretrained(
+    model_id, torch_dtype=torch.bfloat16, device_map="auto"
+)
+
+input_text = "Take a selfie for me with front camera"
+nexa_query = f"Below is the query from the users, please call the correct function and generate the parameters to call the function.\n\nQuery: {input_text} \n\nResponse:"
+start_time = time.time()
+print("nexa model result:\n", inference(nexa_query))
+print("latency:", time.time() - start_time," s")
+```