初始化项目，由ModelHub XC社区提供模型

Model: second-state/Llama-3-8B-Instruct-262k-GGUF Source: Original Platform
2026-06-04 02:21:12 +08:00
commit 9c77625376
17 changed files with 209 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,49 @@
+*.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
+*.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-Instruct-262k-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Llama-3-8B-Instruct-262k-Q2_K.gguf
+++ b/Llama-3-8B-Instruct-262k-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c09e5d2f78bdb4474fa53a78c7bf3cd26e6a8cd59e90913fd95132dd6fd0dfad
+size 3179131104
--- a/Llama-3-8B-Instruct-262k-Q3_K_L.gguf
+++ b/Llama-3-8B-Instruct-262k-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962f1a027f2fad2cbf2a3467e7c2e90bf563d59a6df14d1b291f63bb6d3e39fb
+size 4321956064
--- a/Llama-3-8B-Instruct-262k-Q3_K_M.gguf
+++ b/Llama-3-8B-Instruct-262k-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf07833936ee363300c0782c8d465c44558df41158eadf24d64e82b82a1861a
+size 4018917600
--- a/Llama-3-8B-Instruct-262k-Q3_K_S.gguf
+++ b/Llama-3-8B-Instruct-262k-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae28f9a2908b5e980c41b70ccf7d65011aafbc5aaa852c4a37cec300e8d4239
+size 3664498912
--- a/Llama-3-8B-Instruct-262k-Q4_0.gguf
+++ b/Llama-3-8B-Instruct-262k-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6942d6c73a414df73935b29d069418620e99246ab4efb51b5ade8f348aaae5
+size 4661211360
--- a/Llama-3-8B-Instruct-262k-Q4_K_M.gguf
+++ b/Llama-3-8B-Instruct-262k-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493ce3a6d292d9f4386a20ebd31779a89f7bce9e601341d94d92162cd35b95d5
+size 4920733920
--- a/Llama-3-8B-Instruct-262k-Q4_K_S.gguf
+++ b/Llama-3-8B-Instruct-262k-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f426e7ad648c8fecc66c058146ccece1a6351277cbf6ec1c73f524b9c88fd2d3
+size 4692668640
--- a/Llama-3-8B-Instruct-262k-Q5_0.gguf
+++ b/Llama-3-8B-Instruct-262k-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d59378f3862f2a0f390caf72d84799ca76f4874dde97feee3f616e81a0d1769
+size 5599293664
--- a/Llama-3-8B-Instruct-262k-Q5_K_M.gguf
+++ b/Llama-3-8B-Instruct-262k-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b936c1ec19e1815e31470dd151fb766958e5e8bb605714a2ddc83615ba8a01eb
+size 5732987104
--- a/Llama-3-8B-Instruct-262k-Q5_K_S.gguf
+++ b/Llama-3-8B-Instruct-262k-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807ea6d90a9f66a2acd3d0dd668fd71e2db8c1df5db8483d89b3fadde8296a45
+size 5599293664
--- a/Llama-3-8B-Instruct-262k-Q6_K.gguf
+++ b/Llama-3-8B-Instruct-262k-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05c7911f6f1952e9df84cca53e6b964dd096a3d4883cee46910a8c76ceff62b
+size 6596006112
--- a/Llama-3-8B-Instruct-262k-Q8_0.gguf
+++ b/Llama-3-8B-Instruct-262k-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f310759f6a6f7cfa264062abb03737603095dceefd42ed3286d707a25362988
+size 8540770528
--- a/Llama-3-8B-Instruct-262k-f16.gguf
+++ b/Llama-3-8B-Instruct-262k-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7012103697b68b1f9f10932838ca2c062cebaa5e63b9098ab15acb77454b52
+size 16068890816
--- a/README.md
+++ b/README.md
@@ -0,0 +1,92 @@
+---
+license: other
+license_name: llama3
+base_model: gradientai/Llama-3-8B-Instruct-262k
+inference: false
+model_creator: gradient.ai
+model_type: llama
+pipeline_tag: text-generation
+quantized_by: Second State Inc.
+language:
+- en
+tags:
+- meta
+- llama-3
+---
+
+<!-- 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 -->
+
+# Llama-3-8B-Instruct-262k-GGUF
+
+## Original Model
+
+[gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/gradientai/Llama-3-8B-Instruct-262k)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.8.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.3) and above
+
+- Prompt template
+
+  - Prompt type: `llama-3-chat`
+
+  - Prompt string
+
+    ```text
+    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
+
+    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+    ```
+
+- Context size: `262144`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 262144 \
+    --model-name llama-3-8B-instruct-262k
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-8B-Instruct-262k-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template llama-3-chat \
+    --ctx-size 262144
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Llama-3-8B-Instruct-262k-Q2_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q2_K.gguf)     | Q2_K   | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Llama-3-8B-Instruct-262k-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
+| [Llama-3-8B-Instruct-262k-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
+| [Meta-Llama-3-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
+| [Llama-3-8B-Instruct-262k-Q4_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q4_0.gguf)     | Q4_0   | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Llama-3-8B-Instruct-262k-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
+| [Llama-3-8B-Instruct-262k-Q4_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
+| [Llama-3-8B-Instruct-262k-Q5_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q5_0.gguf)     | Q5_0   | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Llama-3-8B-Instruct-262k-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
+| [Llama-3-8B-Instruct-262k-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
+| [Llama-3-8B-Instruct-262k-Q6_K.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q6_K.gguf)     | Q6_K   | 6 | 6.6 GB| very large, extremely low quality loss |
+| [Llama-3-8B-Instruct-262k-Q8_0.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-Q8_0.gguf)     | Q8_0   | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
+| [Llama-3-8B-Instruct-262k-f16.gguf](https://huggingface.co/second-state/Llama-3-8B-Instruct-262k-GGUF/blob/main/Llama-3-8B-Instruct-262k-f16.gguf)     | f16   | 16 | 16.1 GB|  |
+
+*Quantized with llama.cpp b2734.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "gradientai/Llama-3-8B-Instruct-262k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 262144,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 207112184.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`