初始化项目，由ModelHub XC社区提供模型

Model: second-state/internlm2_5-20b-chat-GGUF Source: Original Platform
2026-07-06 10:43:11 +08:00
commit 8376969d0b
17 changed files with 218 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,48 @@
+*.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
+internlm2_5-20b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm2_5-20b-chat-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,94 @@
+---
+license: other
+pipeline_tag: text-generation
+base_model: internlm/internlm2_5-20b-chat
+model_creator: InternLM
+model_name: internlm2_5-20b-chat
+quantized_by: Second State Inc.
+---
+
+<!-- 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 -->
+
+# internlm2_5-20b-chat-GGUF
+
+## Original Model
+
+[internlm/internlm2_5-20b-chat](https://huggingface.co/internlm/internlm2_5-20b-chat)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: [v0.13.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.13.0) and above
+
+- Prompt template
+
+  - Prompt type: `chatml`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system
+    {system_message}<|im_end|>
+    <|im_start|>user
+    {prompt}<|im_end|>
+    <|im_start|>assistant
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  - Chat
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template chatml \
+      --ctx-size 32000 \
+      --model-name internlm2_5-20b-chat
+    ```
+
+  - Tool use
+
+    ```bash
+    wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+      llama-api-server.wasm \
+      --prompt-template internlm-2-tool \
+      --ctx-size 32000 \
+      --model-name internlm2_5-20b-chat
+    ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. \
+    --nn-preload default:GGML:AUTO:internlm2_5-20b-chat-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [internlm2_5-20b-chat-Q2_K.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q2_K.gguf)     | Q2_K   | 2 | 7.55 GB| smallest, significant quality loss - not recommended for most purposes |
+| [internlm2_5-20b-chat-Q3_K_L.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_L.gguf) | Q3_K_L | 3 | 10.6 GB| small, substantial quality loss |
+| [internlm2_5-20b-chat-Q3_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_M.gguf) | Q3_K_M | 3 | 9.72 GB| very small, high quality loss |
+| [internlm2_5-20b-chat-Q3_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q3_K_S.gguf) | Q3_K_S | 3 | 8.76 GB| very small, high quality loss |
+| [internlm2_5-20b-chat-Q4_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_0.gguf)     | Q4_0   | 4 | 11.3 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [internlm2_5-20b-chat-Q4_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_K_M.gguf) | Q4_K_M | 4 | 12.0 GB| medium, balanced quality - recommended |
+| [internlm2_5-20b-chat-Q4_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q4_K_S.gguf) | Q4_K_S | 4 | 11.4 GB| small, greater quality loss |
+| [internlm2_5-20b-chat-Q5_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_0.gguf)     | Q5_0   | 5 | 13.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [internlm2_5-20b-chat-Q5_K_M.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_K_M.gguf) | Q5_K_M | 5 | 14.1 GB| large, very low quality loss - recommended |
+| [internlm2_5-20b-chat-Q5_K_S.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q5_K_S.gguf) | Q5_K_S | 5 | 13.7 GB| large, low quality loss - recommended |
+| [internlm2_5-20b-chat-Q6_K.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q6_K.gguf)     | Q6_K   | 6 | 16.3 GB| very large, extremely low quality loss |
+| [internlm2_5-20b-chat-Q8_0.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-Q8_0.gguf)     | Q8_0   | 8 | 21.1 GB| very large, extremely low quality loss - not recommended |
+| [internlm2_5-20b-chat-f16.gguf](https://huggingface.co/second-state/internlm2_5-20b-chat-GGUF/blob/main/internlm2_5-20b-chat-f16.gguf)       | f16    | 16 | 39.7 GB|  |
+
+*Quantized with llama.cpp b3499*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "InternLM2ForCausalLM"
+  ],
+  "attn_implementation": "eager",
+  "auto_map": {
+    "AutoConfig": "configuration_internlm2.InternLM2Config",
+    "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
+    "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
+    "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification"
+  },
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 32768,
+  "model_type": "internlm2",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "type": "dynamic",
+    "factor": 2.5
+  },
+  "rope_theta": 50000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 92544
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/internlm2_5-20b-chat-Q2_K.gguf
+++ b/internlm2_5-20b-chat-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e865a42a55067b976d88b3c049e454e21e03bcd3d6b85077b34f5e956dc03974
+size 7546670592
--- a/internlm2_5-20b-chat-Q3_K_L.gguf
+++ b/internlm2_5-20b-chat-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff45b608bffaffb01a02673c5c0fec9d346e0c73606ad3ad0270564290a1005
+size 10551178752
--- a/internlm2_5-20b-chat-Q3_K_M.gguf
+++ b/internlm2_5-20b-chat-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7fdc6ce5941c3172610ccbe6f473ccba135ad70b0caaa1e5ff972c16cd056c
+size 9722279424
--- a/internlm2_5-20b-chat-Q3_K_S.gguf
+++ b/internlm2_5-20b-chat-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb16d145afbcc1f2527962deb50079145d2d281e780dab0c7f359535bb6b3ff
+size 8760473088
--- a/internlm2_5-20b-chat-Q4_0.gguf
+++ b/internlm2_5-20b-chat-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d4ee7370c1edfda367911d771ba28a0286072aec8ba4e9b70f89f8e0d5f9be3
+size 11322686976
--- a/internlm2_5-20b-chat-Q4_K_M.gguf
+++ b/internlm2_5-20b-chat-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc904dbbb9e18494961f7553ab0069a6fd4e4f9a35c3799e83163d79c654ecf0
+size 11984469504
--- a/internlm2_5-20b-chat-Q4_K_S.gguf
+++ b/internlm2_5-20b-chat-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a40f2b746a2440162a9b45328bc08b57dcc1d6e1db86c8e7a291cc628f7558e
+size 11401330176
--- a/internlm2_5-20b-chat-Q5_0.gguf
+++ b/internlm2_5-20b-chat-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d194531c55962c761ab768fdbcb69d251435325d361b05577c818d9f2fbb1a74
+size 13734182400
--- a/internlm2_5-20b-chat-Q5_K_M.gguf
+++ b/internlm2_5-20b-chat-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5504320cb5ffede2d807ed15b93278095a27a5a959285fa22d803bd08a0784a1
+size 14075100672
--- a/internlm2_5-20b-chat-Q5_K_S.gguf
+++ b/internlm2_5-20b-chat-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f380a21b71722138600e414c382cee137ce8096cb0e1079f110e7e94e1c211e
+size 13734182400
--- a/internlm2_5-20b-chat-Q6_K.gguf
+++ b/internlm2_5-20b-chat-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9082b5af0c7daf349ae5556657bb5f6797bf5bd459ed58906d7f75a0ffed35d0
+size 16296396288
--- a/internlm2_5-20b-chat-Q8_0.gguf
+++ b/internlm2_5-20b-chat-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7537641d60a4c944a3d564bdc0134cd9f9df6315e55b761ea19df44db0743c
+size 21106374144
--- a/internlm2_5-20b-chat-f16.gguf
+++ b/internlm2_5-20b-chat-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2890d59c2e17f2d42e9a0e9e538c6349a69f1b387eb4f87900545d86a5313c8
+size 39725643264
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`