readme: update quant info; minor changes to hyperlinks and terms

README.md

@@ -18,9 +18,9 @@ language:
 
 Quantizised from [https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat)
 
-Using llama.cpp b3026 for quantizisation
+Using llama.cpp [b3026](https://github.com/ggerganov/llama.cpp/releases/tag/b3026) for quantizisation. Given the rapid release of llama.cpp builds, this will likely change over time.
 
-# Warning: This will not work unless you set metadata KV overrides, nor will it in LM Studio/similar wrapper apps!
+# Warning: This will not work unless you set metadata KV overrides, nor will it in LM Studio/similar wrapper apps (except supported ones, see below)!
 
 # How to use:
 
@@ -38,11 +38,11 @@ Using llama.cpp b3026 for quantizisation
 
 **Running in llama.cpp:**
 
-To start in command line interactive mode (text completion):
+To start in command line chat mode (chat completion):
 ```
-main -m DeepSeek-V2-Chat.{quant}.gguf -c {context length} --color -i
+main -m DeepSeek-V2-Chat.{quant}.gguf -c {context length} --color -c (-i)
 ```
-To use llama.cpp OpenAI compatible server:
+To use llama.cpp's OpenAI compatible server:
 ```
 server \
   -m DeepSeek-V2-Chat.{quant}.gguf \
@@ -78,11 +78,11 @@ quantize \
 # Quants:
 ```
 - bf16 [size: 439gb]
-- q8_0 [estimated size: 233.27gb]
+- q8_0 (uploading) [size: 233.27gb]
 - q4_k_m [size: 132gb]
 - q2_k [size: 80gb]
 - iq2_xxs [size: 61.5gb]
-- iq3_xs (uploading) [size: 89.6gb]
+- iq3_xs [size: 89.6gb]
 - iq1_m (uploading) [size: 27.3gb]
 - q3_k_m (uploading) [size: 92.6gb]
 ```
@@ -94,18 +94,14 @@ Note: Use iMatrix quants only if you can fully offload to GPU, otherwise speed w
 - q5_k_m
 - q5_k_s
 - q6_k
-- iq4_nl
 - iq4_xs
 - iq2_xs
 - iq2_s
 - iq2_m
-- iq3_xxs
 - iq1_s (note: for fun only, this quant is likely useless)
 ```
 
-Note: the model files do not have some DeepSeek v2 specific parameters, will look into adding them
-
-Please use commit `039896407afd40e54321d47c5063c46a52da3e01`, otherwise use these metadata KV overrides:
+Use these metadata KV overrides (pass them using `--override-kv`, can be specified multiple times):
 ```
 deepseek2.attention.q_lora_rank=int:1536
 deepseek2.attention.kv_lora_rank=int:512
@@ -116,10 +112,12 @@ deepseek2.leading_dense_block_count=int:1
 deepseek2.rope.scaling.yarn_log_multiplier=float:0.0707
 ```
 
+The Q8_0 quant contains these parameters, along with future ones, so as long as you're running a supported build of llama.cpp no `--override-kv` parameters are required.
+
 A precompiled AVX2 version is avaliable at `llama.cpp-039896407afd40e54321d47c5063c46a52da3e01.zip` in the root of this repo.
 
 # License:
-- DeepSeek license for model weights
+- DeepSeek license for model weights, which can be found in the `LICENSE` file in the root of this repo
 - MIT license for any repo code
 
 # Performance: