Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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
+internlm3-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text
+internlm3-8b-instruct.q5_k.gguf filter=lfs diff=lfs merge=lfs -text
+internlm3-8b-instruct.q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+internlm3-8b-instruct.q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+internlm3-8b-instruct.q8_p.gguf filter=lfs diff=lfs merge=lfs -text
+internlm3-8b-instruct.q8q4.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,17 @@
+
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+---
+
+My own (ZeroWw) quantizations.
+output and embed tensors quantized to f16.
+all other tensors quantized to q5_k or q6_k.
+
+Result:
+both f16.q6 and f16.q5 are smaller than q8_0 standard quantization
+and they perform as well as the pure f16.
+
+Updated on: Fri Jan 17, 18:21:06

internlm3-8b-instruct.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d18e16fb05eb24b1145b59b50b169883e270ff01b4dce00d7dd1fc7fa8949dfc
+size 17612430624

internlm3-8b-instruct.q5_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:081f26e4c877b563f5b664d2938a61fcd3dadabb5068073f87fbd157a21f2887
+size 7576182048

internlm3-8b-instruct.q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15891cdee8153a97ec973bb585c18c11b8f918003cb933ce7a14dbf891b6ebf
+size 8468585760

internlm3-8b-instruct.q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396e179911359453bdde732b0a2a5f4ff4b0e3072463a78c5dedff2fb11e7750
+size 10345798944

internlm3-8b-instruct.q8_p.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b07aecc31b35c8041953de9eaac6f0bdbb4583f0b9e4bff218c691bfe80964
+size 9358826784

internlm3-8b-instruct.q8q4.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc149a73c42628c1dbe0e9effd122e8d8529d62833bf88767532ede0c6946cd1
+size 5749300512